Peer Revenue Fully funded

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Robotics

cs.RO Watch Robotics

Monday 19 January

Robotics · Cross-listed from cs.DC

From Design to Deorbit: A Solar-Electric Autonomous Module for Multi-Debris Remediation

Om Mishra, Jayesh Patil, Sathwik Narkedimilli et al. (+3 more)

The escalating accumulation of orbital debris threatens the sustainability of space operations, necessitating active removal solutions that overcome the limitations of current fuel-dependent methods. To address this, this study introduces a novel remediation architecture that integrates a mechanical clamping system for secure capture with a high-efficiency, solar-powered NASA Evolutionary Xenon Thruster (NEXT) and autonomous navigation protocols. High-fidelity simulations validate the architecture's capabilities, demonstrating a successful retrograde deorbit from 800 km to 100 km, <10m position Root Mean Square Errors (RMSE) via radar-based Extended Kalman Filter (EKF) navigation, and a 93% data delivery efficiency within 1 second using Delay/Disruption Tolerant Network (DTN) protocols. This approach significantly advances orbital management by establishing a benchmark for renewable solar propulsion that minimizes reliance on conventional fuels and extends mission longevity for multi-target removal.
Read the full abstract

All authors Om Mishra, Jayesh Patil, Sathwik Narkedimilli, G Srikantha Sharma, Ananda S, Manjunath K Vanahalli

Robotics

FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions

Peng Li, Zihan Zhuang, Yangfan Gao et al. (+16 more)

Humanoid robots are capable of performing various actions such as greeting, dancing and even backflipping. However, these motions are often hard-coded or specifically trained, which limits their versatility. In this work, we present FRoM-W1, an open-source framework designed to achieve general humanoid whole-body motion control using natural language. To universally understand natural language and generate corresponding motions, as well as enable various humanoid robots to stably execute these motions in the physical world under gravity, FRoM-W1 operates in two stages: (a) H-GPT: utilizing massive human data, a large-scale language-driven human whole-body motion generation model is trained to generate diverse natural behaviors. We further leverage the Chain-of-Thought technique to improve the model's generalization in instruction understanding. (b) H-ACT: After retargeting generated human whole-body motions into robot-specific actions, a motion controller that is pretrained and further fine-tuned through reinforcement learning in physical simulation enables humanoid robots to accurately and stably perform corresponding actions. It is then deployed on real robots via a modular simulation-to-reality module. We extensively evaluate FRoM-W1 on Unitree H1 and G1 robots. Results demonstrate superior performance on the HumanML3D-X benchmark for human whole-body motion generation, and our introduced reinforcement learning fine-tuning consistently improves both motion tracking accuracy and task success rates of these humanoid robots. We open-source the entire FRoM-W1 framework and hope it will advance the development of humanoid intelligence.
Read the full abstract

All authors Peng Li, Zihan Zhuang, Yangfan Gao, Yi Dong, Sixian Li, Changhao Jiang, Shihan Dou, Zhiheng Xi, Enyu Zhou, Jixuan Huang, Hui Li, Jingjing Gong, Xingjun Ma, Tao Gui, Zuxuan Wu, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang, Xipeng Qiu

Robotics

Contact-Aware Neural Dynamics

Changwei Jing, Jai Krishna Bandi, Jianglong Ye et al. (+4 more)

High-fidelity physics simulation is essential for scalable robotic learning, but the sim-to-real gap persists, especially for tasks involving complex, dynamic, and discontinuous interactions like physical contacts. Explicit system identification, which tunes explicit simulator parameters, is often insufficient to align the intricate, high-dimensional, and state-dependent dynamics of the real world. To overcome this, we propose an implicit sim-to-real alignment framework that learns to directly align the simulator's dynamics with contact information. Our method treats the off-the-shelf simulator as a base prior and learns a contact-aware neural dynamics model to refine simulated states using real-world observations. We show that using tactile contact information from robotic hands can effectively model the non-smooth discontinuities inherent in contact-rich tasks, resulting in a neural dynamics model grounded by real-world data. We demonstrate that this learned forward dynamics model improves state prediction accuracy and can be effectively used to predict policy performance and refine policies trained purely in standard simulators, offering a scalable, data-driven approach to sim-to-real alignment.
Read the full abstract

All authors Changwei Jing, Jai Krishna Bandi, Jianglong Ye, Yan Duan, Pieter Abbeel, Xiaolong Wang, Sha Yi

Robotics

FocusNav: Spatial Selective Attention with Waypoint Guidance for Humanoid Local Navigation

Yang Zhang, Jianming Ma, Liyun Yan et al. (+4 more)

Robust local navigation in unstructured and dynamic environments remains a significant challenge for humanoid robots, requiring a delicate balance between long-range navigation targets and immediate motion stability. In this paper, we propose FocusNav, a spatial selective attention framework that adaptively modulates the robot's perceptual field based on navigational intent and real-time stability. FocusNav features a Waypoint-Guided Spatial Cross-Attention (WGSCA) mechanism that anchors environmental feature aggregation to a sequence of predicted collision-free waypoints, ensuring task-relevant perception along the planned trajectory. To enhance robustness in complex terrains, the Stability-Aware Selective Gating (SASG) module autonomously truncates distal information when detecting instability, compelling the policy to prioritize immediate foothold safety. Extensive experiments on the Unitree G1 humanoid robot demonstrate that FocusNav significantly improves navigation success rates in challenging scenarios, outperforming baselines in both collision avoidance and motion stability, achieving robust navigation in dynamic and complex environments.
Read the full abstract

All authors Yang Zhang, Jianming Ma, Liyun Yan, Zhanxiang Cao, Yazhou Zhang, Haoyang Li, Yue Gao

Robotics

AirHunt: Bridging VLM Semantics and Continuous Planning for Efficient Aerial Object Navigation

Xuecheng Chen, Zongzhuo Liu, Jianfa Ma et al. (+4 more)

Recent advances in large Vision-Language Models (VLMs) have provided rich semantic understanding that empowers drones to search for open-set objects via natural language instructions. However, prior systems struggle to integrate VLMs into practical aerial systems due to orders-of-magnitude frequency mismatch between VLM inference and real-time planning, as well as VLMs' limited 3D scene understanding. They also lack a unified mechanism to balance semantic guidance with motion efficiency in large-scale environments. To address these challenges, we present AirHunt, an aerial object navigation system that efficiently locates open-set objects with zero-shot generalization in outdoor environments by seamlessly fusing VLM semantic reasoning with continuous path planning. AirHunt features a dual-pathway asynchronous architecture that establishes a synergistic interface between VLM reasoning and path planning, enabling continuous flight with adaptive semantic guidance that evolves through motion. Moreover, we propose an active dual-task reasoning module that exploits geometric and semantic redundancy to enable selective VLM querying, and a semantic-geometric coherent planning module that dynamically reconciles semantic priorities and motion efficiency in a unified framework, enabling seamless adaptation to environmental heterogeneity. We evaluate AirHunt across diverse object navigation tasks and environments, demonstrating a higher success rate with lower navigation error and reduced flight time compared to state-of-the-art methods. Real-world experiments further validate AirHunt's practical capability in complex and challenging environments. Code and dataset will be made publicly available before publication.
Read the full abstract

All authors Xuecheng Chen, Zongzhuo Liu, Jianfa Ma, Bang Du, Tiantian Zhang, Xueqian Wang, Boyu Zhou

Robotics · Cross-listed from cs.CV

DC-VLAQ: Query-Residual Aggregation for Robust Visual Place Recognition

Hanyu Zhu, Zhihao Zhan, Yuhang Ming et al. (+4 more)

One of the central challenges in visual place recognition (VPR) is learning a robust global representation that remains discriminative under large viewpoint changes, illumination variations, and severe domain shifts. While visual foundation models (VFMs) provide strong local features, most existing methods rely on a single model, overlooking the complementary cues offered by different VFMs. However, exploiting such complementary information inevitably alters token distributions, which challenges the stability of existing query-based global aggregation schemes. To address these challenges, we propose DC-VLAQ, a representation-centric framework that integrates the fusion of complementary VFMs and robust global aggregation. Specifically, we first introduce a lightweight residual-guided complementary fusion that anchors representations in the DINOv2 feature space while injecting complementary semantics from CLIP through a learned residual correction. In addition, we propose the Vector of Local Aggregated Queries (VLAQ), a query–residual global aggregation scheme that encodes local tokens by their residual responses to learnable queries, resulting in improved stability and the preservation of fine-grained discriminative cues. Extensive experiments on standard VPR benchmarks, including Pitts30k, Tokyo24/7, MSLS, Nordland, SPED, and AmsterTime, demonstrate that DC-VLAQ consistently outperforms strong baselines and achieves state-of-the-art performance, particularly under challenging domain shifts and long-term appearance changes.
Read the full abstract

All authors Hanyu Zhu, Zhihao Zhan, Yuhang Ming, Liang Li, Dibo Hou, Javier Civera, Wanzeng Kong

Robotics

RPT*: Global Planning with Probabilistic Terminals for Target Search in Complex Environments

Yunpeng Lyu, Chao Cao, Ji Zhang et al. (+2 more)

Routing problems such as Hamiltonian Path Problem (HPP), seek a path to visit all the vertices in a graph while minimizing the path cost. This paper studies a variant, HPP with Probabilistic Terminals (HPP-PT), where each vertex has a probability representing the likelihood that the robot's path terminates there, and the objective is to minimize the expected path cost. HPP-PT arises in target object search, where a mobile robot must visit all candidate locations to find an object, and prior knowledge of the object's location is expressed as vertex probabilities. While routing problems have been studied for decades, few of them consider uncertainty as required in this work. The challenge lies not only in optimality ordering the vertices, as in standard HPP, but also in handling history dependency: the expected path cost depends on the order in which vertices were previously visited. This makes many existing methods inefficient or inapplicable. To address the challenge, we propose a search-based approach RPT* with solution optimality guarantees, which leverages dynamic programming in a new state space to bypass the history dependency and novel heuristics to speed up the computation. Building on RPT*, we design a Hierarchical Autonomous Target Search (HATS) system that combines RPT* with either Bayesian filtering for lifelong target search with noisy sensors, or autonomous exploration to find targets in unknown environments. Experiments in both simulation and real robot show that our approach can naturally balance between exploitation and exploration, thereby finding targets more quickly on average than baseline methods.
Read the full abstract

All authors Yunpeng Lyu, Chao Cao, Ji Zhang, Howie Choset, Zhongqiang Ren

Sunday 18 January

Robotics · Cross-listed from cs.HC

An Embodied Companion for Visual Storytelling

Patrick Tresset and Markus Wulfmeier

As artificial intelligence shifts from pure tool for delegation toward agentic collaboration, its use in the arts can shift beyond the exploration of machine autonomy toward synergistic co-creation. While our earlier robotic works utilized automation to distance the artist's intent from the final mark, we present Companion: an artistic apparatus that integrates a drawing robot with Large Language Models (LLMs) to re-center human-machine presence. By leveraging in-context learning and real-time tool use, the system engages in bidirectional interaction via speech and sketching. This approach transforms the robot from a passive executor into a playful co-creative partner capable of driving shared visual storytelling into unexpected aesthetic territories. To validate this collaborative shift, we employed the Consensual Assessment Technique (CAT) with a panel of seven art-world experts. Results confirm that the system produces works with a distinct aesthetic identity and professional exhibition merit, demonstrating the potential of AI as a highly capable artistic collaborator.
Read the full abstract

Robotics

UAVGENT: A Language-Guided Distributed Control Framework

Ziyi Zhang, Xiyu Deng, Guannan Qu et al. (+1 more)

We study language-in-the-loop control for multi-drone systems that execute evolving, high-level missions while retaining formal robustness guarantees at the physical layer. We propose a three-layer architecture in which (i) a human operator issues natural-language instructions, (ii) an LLM-based supervisor periodically interprets, verifies, and corrects the commanded task in the context of the latest state and target estimates, and (iii) a distributed inner-loop controller tracks the resulting reference using only local relative information. We derive a theoretical guarantee that characterizes tracking performance under bounded disturbances and piecewise-smooth references with discrete jumps induced by LLM updates. Overall, our results illustrate how centralized language-based task reasoning can be combined with distributed feedback control to achieve complex behaviors with provable robustness and stability.
Read the full abstract

All authors Ziyi Zhang, Xiyu Deng, Guannan Qu, Yorie Nakahira

Robotics

Autonomous Manipulation of Hazardous Chemicals and Delicate Objects in a Self-Driving Laboratory: A Sliding Mode Approach

Shifa Sulaiman, Francesco Schetter, Tobias Jensen et al. (+2 more)

Precise handling of chemical instruments and materials within a self-driving laboratory environment using robotic systems demands advanced and reliable control strategies. Sliding Mode Control (SMC) has emerged as a robust approach for managing uncertainties and disturbances in manipulator dynamics, providing superior control performance compared to traditional methods. This study implements a model-based SMC (MBSMC) utilizing a hyperbolic tangent function to regulate the motion of a manipulator mounted on a mobile platform operating inside a self-driving chemical laboratory. Given the manipulator's role in transporting fragile glass vessels filled with hazardous chemicals, the controller is specifically designed to minimize abrupt transitions and achieve gentle, accurate trajectory tracking. The proposed controller is benchmarked against a non-model-based SMC (NMBSMC) and a Proportional-Integral-Derivative (PID) controller using a comprehensive set of joint and Cartesian metrics. Compared to PID and NMBSMC, MBSMC achieved significantly smoother motion and up to 90% lower control effort, validating its robustness and precision for autonomous laboratory operations. Experimental trials confirmed successful execution of tasks such as vessel grasping and window operation, which failed under PID control due to its limited ability to handle nonlinear dynamics and external disturbances, resulting in substantial trajectory tracking errors. The results validate the controller's effectiveness in achieving smooth, precise, and safe manipulator motions, supporting the advancement of intelligent mobile manipulators in autonomous laboratory environments.
Read the full abstract

All authors Shifa Sulaiman, Francesco Schetter, Tobias Jensen, Simon Bøgh, Fanny Ficuciello

Robotics

Enabling High-Curvature Navigation in Eversion Robots through Buckle-Inducing Constrictive Bands

Cem Suulker, Muhie Al Haimus, Thomas Mack et al. (+10 more)

Tip-growing eversion robots are renowned for their ability to access remote spaces through narrow passages. However, achieving reliable navigation remains a significant challenge. Existing solutions often rely on artificial muscles integrated into the robot body or active tip-steering mechanisms. While effective, these additions introduce structural complexity and compromise the defining advantages of eversion robots: their inherent softness and compliance. In this paper, we propose a passive approach to reduce bending stiffness by purposefully introducing buckling points along the robot's outer wall. We achieve this by integrating inextensible diameter-reducing circumferential bands at regular intervals along the robot body facilitating forward motion through tortuous, obstacle cluttered paths. Rather than relying on active steering, our approach leverages the robot's natural interaction with the environment, allowing for smooth, compliant navigation. We present a Cosserat rod-based mathematical model to quantify this behavior, capturing the local stiffness reductions caused by the constricting bands and their impact on global bending mechanics. Experimental results demonstrate that these bands reduce the robot's stiffness when bent at the tip by up to 91 percent, enabling consistent traversal of 180 degree bends with a bending radius of as low as 25 mm-notably lower than the 35 mm achievable by standard eversion robots under identical conditions. The feasibility of the proposed method is further demonstrated through a case study in a colon phantom. By significantly improving maneuverability without sacrificing softness or increasing mechanical complexity, this approach expands the applicability of eversion robots in highly curved pathways, whether in relation to pipe inspection or medical procedures such as colonoscopy.
Read the full abstract

All authors Cem Suulker, Muhie Al Haimus, Thomas Mack, Mohammad Sheikhsofla, Neri Niccolò Dei, Reza Kashef, Hadi Sadati, Federica Barontini, Fanny Ficuciello, Alberto Arezzo, Bruno Siciliano, Sebastien Ourselin, Kaspar Althoefer

Robotics

Language-Based Swarm Perception: Decentralized Person Re-Identification via Natural Language Descriptions

Miquel Kegeleirs, Lorenzo Garattoni, Gianpiero Francesca et al. (+1 more)

We introduce a method for decentralized person re-identification in robot swarms that leverages natural language as the primary representational modality. Unlike traditional approaches that rely on opaque visual embeddings – high-dimensional feature vectors extracted from images – the proposed method uses human-readable language to represent observations. Each robot locally detects and describes individuals using a vision-language model (VLM), producing textual descriptions of appearance instead of feature vectors. These descriptions are compared and clustered across the swarm without centralized coordination, allowing robots to collaboratively group observations of the same individual. Each cluster is distilled into a representative description by a language model, providing an interpretable, concise summary of the swarm's collective perception. This approach enables natural-language querying, enhances transparency, and supports explainable swarm behavior. Preliminary experiments demonstrate competitive performance in identity consistency and interpretability compared to embedding-based methods, despite current limitations in text similarity and computational load. Ongoing work explores refined similarity metrics, semantic navigation, and the extension of language-based perception to environmental elements. This work prioritizes decentralized perception and communication, while active navigation remains an open direction for future study.
Read the full abstract

All authors Miquel Kegeleirs, Lorenzo Garattoni, Gianpiero Francesca, Mauro Birattari

Robotics

KILO-EKF: Koopman-Inspired Learned Observations Extended Kalman Filter

Zi Cong Guo, James R. Forbes and Timothy D. Barfoot

We present the Koopman-Inspired Learned Observations Extended Kalman Filter (KILO-EKF), which combines a standard EKF prediction step with a correction step based on a Koopman-inspired measurement model learned from data. By lifting measurements into a feature space where they are linear in the state, KILO-EKF enables flexible modeling of complex or poorly calibrated sensors while retaining the structure and efficiency of recursive filtering. The resulting linear-Gaussian measurement model is learned in closed form from groundtruth training data, without iterative optimization or reliance on an explicit parametric sensor model. At inference, KILO-EKF performs a standard EKF update using Jacobians obtained via the learned lifting. We validate the approach on a real-world quadrotor localization task using an IMU, ultra-wideband (UWB) sensors, and a downward-facing laser. We compare against multiple EKF baselines with varying levels of sensor calibration. KILO-EKF achieves better accuracy and consistency compared to data-calibrated baselines, and significantly outperforms EKFs that rely on imperfect geometric models, while maintaining real-time inference and fast training. These results demonstrate the effectiveness of Koopman-inspired measurement learning as a scalable alternative to traditional model-based calibration.
Read the full abstract

Robotics

ReWorld: Multi-Dimensional Reward Modeling for Embodied Video Generation

Baorui Peng, Wenyao Zhang, Liang Xu et al. (+7 more)

Current embodied video generation models primarily emphasize visual generative quality while overlooking physical fidelity, dynamic consistency, and task logic, especially for contact-rich manipulation tasks, which limits their applicability to downstream tasks. In this paper, we introduce ReWorld, a framework aimed to employ reinforcement learning to align the video generation with physical realism, task completion capability, embodiment plausibility and visual quality. Specifically, we first construct a large-scale (~235K) video preference dataset and employ it to train a hierarchical reward model designed to capture multi-dimensional reward consistent with human preferences. We further propose a practical alignment algorithm that post-trains flow-based video generators using this reward through a computationally efficient PPO-style algorithm. Comprehensive experiments and theoretical analysis demonstrate that ReWorld significantly improves the physical fidelity, logical coherence, embodiment and visual quality of generated rollouts, outperforming previous methods.
Read the full abstract

All authors Baorui Peng, Wenyao Zhang, Liang Xu, Bohan Li, Hu Zhu, Zekun Qi, Hongsi Liu, Jiazhao Zhang, Wenjun Zeng, Xin Jin

Robotics

Learning Diverse Skills for Behavior Models with Mixture of Experts

Wangtian Shen, Jinming Ma, Mingliang Zhou et al. (+1 more)

Imitation learning has demonstrated strong performance in robotic manipulation by learning from large-scale human demonstrations. While existing models excel at single-task learning, it is observed in practical applications that their performance degrades in the multi-task setting, where interference across tasks leads to an averaging effect. To address this issue, we propose to learn diverse skills for behavior models with Mixture of Experts, referred to as Di-BM. Di-BM associates each expert with a distinct observation distribution, enabling experts to specialize in sub-regions of the observation space. Specifically, we employ energy-based models to represent expert-specific observation distributions and jointly train them alongside the corresponding action models. Our approach is plug-and-play and can be seamlessly integrated into standard imitation learning methods. Extensive experiments on multiple real-world robotic manipulation tasks demonstrate that Di-BM significantly outperforms state-of-the-art baselines. Moreover, fine-tuning the pretrained Di-BM on novel tasks exhibits superior data efficiency and the reusable of expert-learned knowledge. Code is available at https://github.com/robotnav-bot/Di-BM.
Read the full abstract

All authors Wangtian Shen, Jinming Ma, Mingliang Zhou, Ziyang Meng

Robotics

XR$^3$: An Extended Reality Platform for Social-Physical Human-Robot Interaction

Chao Wang, Anna Belardinelli and Michael Gienger

Social-physical human-robot interaction (spHRI) is difficult to study: building and programming robots that integrate multiple interaction modalities is costly and slow, while VR-based prototypes often lack physical contact, breaking users' visuo-tactile expectations. We present XR$^3$, a co-located dual-VR-headset platform for HRI research in which an attendee and a hidden operator share the same physical space while experiencing different virtual embodiments. The attendee sees an expressive virtual robot that interacts face-to-face in a shared virtual environment. In real time, the robot's upper-body motion, head and gaze behavior, and facial expressions are mapped from the operator's tracked limbs and face signals. Because the operator is co-present and calibrated in the same coordinate frame, the operator can also touch the attendee, enabling perceived robot touch synchronized with the robot's visible hands. Finger and hand motion is mapped to the robot avatar using inverse kinematics to support precise contact. Beyond motion retargeting, XR$^3$ supports social retargeting of multiple nonverbal cues that can be experimentally varied while keeping physical interaction constant. We detail the system design and calibration, and demonstrate the platform in a touch-based Wizard-of-Oz study, lowering the barrier to prototyping and evaluating embodied, contact-based robot behaviors.
Read the full abstract

Robotics

R-VoxelMap: Accurate Voxel Mapping with Recursive Plane Fitting for Online LiDAR Odometry

Haobo Xi, Shiyong Zhang, Qianli Dong et al. (+4 more)

This paper proposes R-VoxelMap, a novel voxel mapping method that constructs accurate voxel maps using a geometry-driven recursive plane fitting strategy to enhance the localization accuracy of online LiDAR odometry. VoxelMap and its variants typically fit and check planes using all points in a voxel, which may lead to plane parameter deviation caused by outliers, over segmentation of large planes, and incorrect merging across different physical planes. To address these issues, R-VoxelMap utilizes a geometry-driven recursive construction strategy based on an outlier detect-and-reuse pipeline. Specifically, for each voxel, accurate planes are first fitted while separating outliers using random sample consensus (RANSAC). The remaining outliers are then propagated to deeper octree levels for recursive processing, ensuring a detailed representation of the environment. In addition, a point distribution-based validity check algorithm is devised to prevent erroneous plane merging. Extensive experiments on diverse open-source LiDAR(-inertial) simultaneous localization and mapping (SLAM) datasets validate that our method achieves higher accuracy than other state-of-the-art approaches, with comparable efficiency and memory usage. Code will be available on GitHub.
Read the full abstract

All authors Haobo Xi, Shiyong Zhang, Qianli Dong, Yunze Tong, Songyang Wu, Jing Yuan, Xuebo Zhang

Robotics · Cross-listed from cs.CV

CD-TWINSAFE: A ROS-enabled Digital Twin for Scene Understanding and Safety Emerging V2I Technology

Amro Khaled, Farah Khaled, Omar Riad et al. (+1 more)

In this paper, the CD-TWINSAFE is introduced, a V2I-based digital twin for Autonomous Vehicles. The proposed architecture is composed of two stacks running simultaneously, an on-board driving stack that includes a stereo camera for scene understanding, and a digital twin stack that runs an Unreal Engine 5 replica of the scene viewed by the camera as well as returning safety alerts to the cockpit. The on-board stack is implemented on the vehicle side including 2 main autonomous modules; localization and perception. The position and orientation of the ego vehicle are obtained using on-board sensors. Furthermore, the perception module is responsible for processing 20-fps images from stereo camera and understands the scene through two complementary pipelines. The pipeline are working on object detection and feature extraction including object velocity, yaw and the safety metrics time-to-collision and time-headway. The collected data form the driving stack are sent to the infrastructure side through the ROS-enabled architecture in the form of custom ROS2 messages and sent over UDP links that ride a 4G modem for V2I communication. The environment is monitored via the digital twin through the shared messages which update the information of the spawned ego vehicle and detected objects based on the real-time localization and perception data. Several tests with different driving scenarios to confirm the validity and real-time response of the proposed architecture.
Read the full abstract

All authors Amro Khaled, Farah Khaled, Omar Riad, Catherine M. Elias

Robotics · Cross-listed from cs.HC

User-to-Vehicle Interaction in Smart Mobility: The GO-DRiVeS Autonomous Ride-Sharing Application

Hana E. Elmalah and Catherine M. Elias

This paper introduces the GO-DRiVeS application, an on demand ride sharing and requesting mobile application tailored specifically to save long walks and challenges which are time consuming and tiring especially during hot days or when carrying heavy items, faced by university students and staff. The GO-DRiVeS application was developed following the Agile methodology for its flexibility. In addition to, using the mobile application system architecture and client-server architecture. GO-DRiVeS was implemented using React Native (Expo) for the frontend, Node.js and Express for the backend, and MongoDB as the database; based on a detailed analyses to the existing transportation application, comparing their frameworks and identifying their essential functionalities. GO-DRiVeS supports core features like user registration, ride requesting and real-time tracking.In addition to handling multiple requests at the same time in a first come first serve manner. The application was developed based on these features, and the results were conducted in the form of multiple experiments that demonstrated stable behavior in handling the requests, as presented in the Methodology and Results chapters.
Read the full abstract

Robotics · Cross-listed from cs.CV

From Prompts to Pavement: LMMs-based Agentic Behavior-Tree Generation Framework for Autonomous Vehicles

Omar Y. Goba, Ahmed Y. Gado, Catherine M. Elias et al. (+1 more)

Autonomous vehicles (AVs) require adaptive behavior planners to navigate unpredictable, real-world environments safely. Traditional behavior trees (BTs) offer structured decision logic but are inherently static and demand labor-intensive manual tuning, limiting their applicability at SAE Level 5 autonomy. This paper presents an agentic framework that leverages large language models (LLMs) and multi-modal vision models (LVMs) to generate and adapt BTs on the fly. A specialized Descriptor agent applies chain-of-symbols prompting to assess scene criticality, a Planner agent constructs high-level sub-goals via in-context learning, and a Generator agent synthesizes executable BT sub-trees in XML format. Integrated into a CARLA+Nav2 simulation, our system triggers only upon baseline BT failure, demonstrating successful navigation around unexpected obstacles (e.g., street blockage) with no human intervention. Compared to a static BT baseline, this approach is a proof-of-concept that extends to diverse driving scenarios.
Read the full abstract

All authors Omar Y. Goba, Ahmed Y. Gado, Catherine M. Elias, Ahmed Hussein

Robotics

From Shallow Waters to Mariana Trench: A Survey of Bio-inspired Underwater Soft Robots

Jie Wang, Peng Du, Yiyuan Zhang et al. (+2 more)

Sample Exploring the ocean environment holds profound significance in areas such as resource exploration and ecological protection. Underwater robots struggle with extreme water pressure and often cause noise and damage to the underwater ecosystem, while bio-inspired soft robots draw inspiration from aquatic creatures to address these challenges. These bio-inspired approaches enable robots to withstand high water pressure, minimize drag, operate with efficient manipulation and sensing systems, and interact with the environment in an eco-friendly manner. Consequently, bio-inspired soft robots have emerged as a promising field for ocean exploration. This paper reviews recent advancements in underwater bio-inspired soft robots, analyses their design considerations when facing different desired functions, bio-inspirations, ambient pressure, temperature, light, and biodiversity , and finally explores the progression from bio-inspired principles to practical applications in the field and suggests potential directions for developing the next generation of underwater soft robots.
Read the full abstract

All authors Jie Wang, Peng Du, Yiyuan Zhang, Zhexin Xie, Cecilia Laschi

Robotics

OpenNavMap: Multi-Session Appearance-Based Topometric Mapping for Scalable Visual Navigation

Jianhao Jiao, Changkun Liu, Jingwen Yu et al. (+4 more)

Scalable and maintainable maps are fundamental to large-scale navigation and the long-term deployment of robots in real-world environments. However, conventional maps that explicitly maintain dense geometry or 3D landmarks incur high storage and maintenance costs, while the core challenge of scaling to multi-session mapping is visual localization under sparse viewpoint overlap, temporal appearance shifts, and cross-device variance. To address this, we propose OpenNavMap, a lightweight, landmark-free topometric mapping system that organizes image nodes into covisibility, odometry, and traversability graphs and delegates local geometry recovery to 3D geometric foundation models (GFMs) on demand. For localization, dynamic-programming-based sequence matching narrows candidate correspondences for a GFM, reducing global estimation to a lightweight, pose-only optimization; for mapping, a lifelong pipeline fuses multi-session, multi-device data via cross-device merging and node culling. On a 19km dataset across four real-world environments, \methodname attains a state-of-the-art $0.62$m translation error on the Map-Free benchmark, bounds the absolute trajectory error below $3$m across 15.7km without depth sensors, and completes $12$ autonomous image-goal visual navigation tasks on both simulated and physical robots. Code and datasets will be made publicly available at https://rpl-cs-ucl.github.io/OpenNavMap_page.
Read the full abstract

All authors Jianhao Jiao, Changkun Liu, Jingwen Yu, Boyi Liu, Qianyi Zhang, Yue Wang, Dimitrios Kanoulas

Robotics

An Efficient and Multi-Modal Navigation System with One-Step World Model

Wangtian Shen, Ziyang Meng, Jinming Ma et al. (+2 more)

Navigation is a fundamental capability for mobile robots. While the current trend is to use learning-based approaches to replace traditional geometry-based methods, existing end-to-end learning-based policies often struggle with 3D spatial reasoning and lack a comprehensive understanding of physical world dynamics. Integrating world models-which predict future observations conditioned on given actions-with iterative optimization planning offers a promising solution due to their capacity for imagination and flexibility. However, current navigation world models, typically built on pure transformer architectures, often rely on multi-step diffusion processes and autoregressive frame-by-frame generation. These mechanisms result in prohibitive computational latency, rendering real-time deployment impossible. To address this bottleneck, we propose a lightweight navigation world model that adopts a one-step generation paradigm and a 3D U-Net backbone equipped with efficient spatial-temporal attention. This design drastically reduces inference latency, enabling high-frequency control while achieving superior predictive performance. We also integrate this model into an optimization-based planning framework utilizing anchor-based initialization to handle multi-modal goal navigation tasks. Extensive closed-loop experiments in both simulation and real-world environments demonstrate our system's superior efficiency and robustness compared to state-of-the-art baselines.
Read the full abstract

All authors Wangtian Shen, Ziyang Meng, Jinming Ma, Mingliang Zhou, Diyun Xiang

Robotics

A Comprehensive Review of Bio-Inspired Approaches to Coordination, Communication, and System Architecture in Underwater Swarm Robotics

Shyalan Ramesh, Scott Mann and Alex Stumpf

The increasing complexity of marine operations has intensified the need for intelligent robotic systems to support ocean observation, exploration, and resource management. Underwater swarm robotics offers a promising framework that extends the capabilities of individual autonomous platforms through collective coordination. Inspired by natural systems, such as fish schools and insect colonies, bio-inspired swarm approaches enable distributed decision-making, adaptability, and resilience under challenging marine conditions. Yet research in this field remains fragmented, with limited integration across algorithmic, communication, and hardware design perspectives. This review synthesises bio-inspired coordination mechanisms, communication strategies, and system design considerations for underwater swarm robotics. It examines key marine-specific algorithms, including the Artificial Fish Swarm Algorithm, Whale Optimisation Algorithm, Coral Reef Optimisation, and Marine Predators Algorithm, highlighting their applications in formation control, task allocation, and environmental interaction. The review also analyses communication constraints unique to the underwater domain and emerging acoustic, optical, and hybrid solutions that support cooperative operation. Additionally, it examines hardware and system design advances that enhance system efficiency and scalability. A multi-dimensional classification framework evaluates existing approaches across communication dependency, environmental adaptability, energy efficiency, and swarm scalability. Through this integrated analysis, the review unifies bio-inspired coordination algorithms, communication modalities, and system design approaches. It also identifies converging trends, key challenges, and future research directions for real-world deployment of underwater swarm systems.
Read the full abstract

Saturday 17 January

Robotics

Learning Legged MPC with Smooth Neural Surrogates

Samuel A. Moore, Easop Lee and Boyuan Chen

Deep learning and model predictive control (MPC) can play complementary roles in legged robotics. However, integrating learned models with online planning remains challenging. When dynamics are learned with neural networks, three key difficulties arise: (1) stiff transitions from contact events may be inherited from the data; (2) additional non-physical local nonsmoothness can occur; and (3) training datasets can induce non-Gaussian model errors due to rapid state changes. We address (1) and (2) by introducing the smooth neural surrogate, a neural network with tunable smoothness designed to provide informative predictions and derivatives for trajectory optimization through contact. To address (3), we train these models using a heavy-tailed likelihood that better matches the empirical error distributions observed in legged-robot dynamics. Together, these design choices substantially improve the reliability, scalability, and generalizability of learned legged MPC. Across zero-shot locomotion tasks of increasing difficulty, smooth neural surrogates with robust learning yield consistent reductions in cumulative cost on simple, well-conditioned behaviors (typically 10-50%), while providing substantially larger gains in regimes where standard neural dynamics often fail outright. In these regimes, smoothing enables reliable execution (from 0/5 to 5/5 success) and produces about 2-50x lower cumulative cost, reflecting orders-of-magnitude absolute improvements in robustness rather than incremental performance gains.
Read the full abstract

Robotics

Neural Process-Based Reactive Controller for Autonomous Racing

Devin Hunter and Chinwendu Enyioha

Attention-based neural architectures have become central to state-of-the-art methods in real-time nonlinear control. As these data-driven models continue to be integrated into increasingly safety-critical domains, ensuring statistically grounded and provably safe decision-making becomes essential. This paper introduces a novel reactive control framework for gap-based navigation using the Attentive Neural Process (AttNP) and a physics-informed extension, the PI-AttNP. Both models are evaluated in a simulated F1TENTH-style Ackermann steering racecar environment, chosen as a fast-paced proxy for safety-critical autonomous driving scenarios. The PI-AttNP augments the AttNP architecture with approximate model-based priors to inject physical inductive bias, enabling faster convergence and improved prediction accuracy suited for real-time control. To further ensure safety, we derive and implement a control barrier function (CBF)-based filtering mechanism that analytically enforces collision avoidance constraints. This CBF formulation is fully compatible with the learned AttNP controller and generalizes across a wide range of racing scenarios, providing a lightweight and certifiable safety layer. Our results demonstrate competitive closed-loop performance while ensuring real-time constraint satisfaction.
Read the full abstract

Robotics · Cross-listed from eess.AS

Listen, Look, Drive: Coupling Audio Instructions for User-aware VLA-based Autonomous Driving

Ziang Guo, Feng Yang, Xuefeng Zhang et al. (+6 more)

Vision Language Action (VLA) models promise an open-vocabulary interface that can translate perceptual ambiguity into semantically grounded driving decisions, yet they still treat language as a static prior fixed at inference time. As a result, the model must infer continuously shifting objectives from pixels alone, yielding delayed or overly conservative maneuvers. We argue that effective VLAs for autonomous driving need an online channel in which users can influence driving with specific intentions. To this end, we present EchoVLA, a user-aware VLA that couples camera streams with in situ audio instructions. We augment the nuScenes dataset with temporally aligned, intent-specific speech commands generated by converting ego-motion descriptions into synthetic audios. Further, we compose emotional speech-trajectory pairs into a multimodal Chain-of-Thought (CoT) for fine-tuning a Multimodal Large Model (MLM) based on Qwen2.5-Omni. Specifically, we synthesize the audio-augmented dataset with different emotion types paired with corresponding driving behaviors, leveraging the emotional cues embedded in tone, pitch, and speech tempo to reflect varying user states, such as urgent or hesitant intentions, thus enabling our EchoVLA to interpret not only the semantic content but also the emotional context of audio commands for more nuanced and emotionally adaptive driving behavior. In open-loop benchmarks, our approach reduces the average L2 error by $59.4\%$ and the collision rate by $74.4\%$ compared to the baseline of vision-only perception. More experiments on nuScenes dataset validate that EchoVLA not only steers the trajectory through audio instructions, but also modulates driving behavior in response to the emotions detected in the user's speech.
Read the full abstract

All authors Ziang Guo, Feng Yang, Xuefeng Zhang, Jiaqi Guo, Kun Zhao, Yixiao Zhou, Peng Lu, Sifa Zheng, Zufeng Zhang

Robotics

OctoSplat: Hybrid OctoMap-Gaussian Splatting for Active Semantic Mapping and Phenotyping with Horticultural Robots

Jose Cuaran, Naveen K. Uppalapati and Girish Chowdhary

Semantic reconstruction of agricultural scenes plays a vital role in tasks such as phenotyping and yield estimation. However, traditional approaches based on manual scanning or fixed camera setups remain a major bottleneck, while active-mapping methods based solely on occupancy grids are too coarse for accurate trait estimation. To address this gap, we propose an active 3D reconstruction framework for horticultural environments using a mobile manipulator. The system integrates OctoMap with 3D Gaussian Splatting to enable accurate and efficient target-aware mapping. A low-resolution OctoMap provides probabilistic occupancy information for informative viewpoint selection and collision-free planning, while 3D Gaussian Splatting leverages geometric, photometric, and semantic information to optimize 3D Gaussians for high-fidelity scene reconstruction. We further introduce a robust mapping strategy that mitigates semantic segmentation and depth noise, together with a background pruning method that reduces memory and computational cost. We validate our framework across simulated, laboratory, and real greenhouse scenes, showing consistent improvements across three state-of-the-art Gaussian Splatting backbones. In simulation, where ground-truth geometry is available, our approach outperforms occupancy-based mapping in both reconstruction accuracy and runtime efficiency: compared with a 0.01m-resolution OctoMap, it doubles the fruit-level F1 score under noisy conditions while achieving up to a threefold reduction in runtime. Beyond simulation, novel-view synthesis quality also improves consistently in laboratory and real greenhouse environments, with PSNR and mIoU improving by up to 1.5 dB and 18%, respectively. Finally, the reconstructed semantic maps enable fruit counting and volume estimation with accuracies approaching 80%.
Read the full abstract

Robotics

BiKC+: Bimanual Hierarchical Imitation with Keypose-Conditioned Coordination-Aware Consistency Policies

Hang Xu, Yizhou Chen, Dongjie Yu et al. (+2 more)

Robots are essential in industrial manufacturing due to their reliability and efficiency. They excel in performing simple and repetitive unimanual tasks but still face challenges with bimanual manipulation. This difficulty arises from the complexities of coordinating dual arms and handling multi-stage processes. Recent integration of generative models into imitation learning (IL) has made progress in tackling specific challenges. However, few approaches explicitly consider the multi-stage nature of bimanual tasks while also emphasizing the importance of inference speed. In multi-stage tasks, failures or delays at any stage can cascade over time, impacting the success and efficiency of subsequent sub-stages and ultimately hindering overall task performance. In this paper, we propose a novel keypose-conditioned coordination-aware consistency policy tailored for bimanual manipulation. Our framework instantiates hierarchical imitation learning with a high-level keypose predictor and a low-level trajectory generator. The predicted keyposes serve as sub-goals for trajectory generation, indicating targets for individual sub-stages. The trajectory generator is formulated as a consistency model, generating action sequences based on historical observations and predicted keyposes in a single inference step. In particular, we devise an innovative approach for identifying bimanual keyposes, considering both robot-centric action features and task-centric operation styles. Simulation and real-world experiments illustrate that our approach significantly outperforms baseline methods in terms of success rates and operational efficiency. Implementation codes can be found at https://github.com/JoanaHXU/BiKC-plus.
Read the full abstract

All authors Hang Xu, Yizhou Chen, Dongjie Yu, Yi Ren, Jia PanI

Robotics · Cross-listed from cs.AR

Domain-specific Hardware Acceleration for Model Predictive Path Integral Control

Erwan Tanguy-Legac, Tommaso Belvedere, Gianluca Corsini et al. (+2 more)

Accurately controlling a robotic system in real time is a challenging problem. To address this, the robotics community has adopted various algorithms, such as Model Predictive Control (MPC) and Model Predictive Path Integral (MPPI) control. The first is difficult to implement on non-linear systems such as unmanned aerial vehicles, whilst the second requires a heavy computational load. GPUs have been successfully used to accelerate MPPI implementations; however, their power consumption is often excessive for autonomous or unmanned targets, especially when battery-powered. On the other hand, custom designs, often implemented on FPGAs, have been proposed to accelerate robotic algorithms while consuming considerably less energy than their GPU (or CPU) implementation. However, no MPPI custom accelerator has been proposed so far. In this work, we present a hardware accelerator for MPPI control and simulate its execution. Results show that the MPPI custom accelerator allows more accurate trajectories than GPU-based MPPI implementations.
Read the full abstract

All authors Erwan Tanguy-Legac, Tommaso Belvedere, Gianluca Corsini, Marco Tognon, Marcello Traiola