Peer Revenue Returns subject to peer review

Papers

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

Computer Science Robotics

cs.RO Watch Robotics

Wednesday 17 December

Robotics · Cross-listed from cs.CV

R4: Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Space

Tin Stribor Sohn, Maximilian Dillitzer, Jason J. Corso et al. (+1 more)

Humans perceive and reason about their surroundings in four dimensions by building persistent, structured internal representations that encode semantic meaning, spatial layout, and temporal dynamics. These multimodal memories enable them to recall past events, infer unobserved states, and integrate new information into context-dependent reasoning. Inspired by this capability, we introduce R4, a training-free framework for retrieval-augmented reasoning in 4D spatio-temporal space that equips vision-language models (VLMs) with structured, lifelong memory. R4 continuously constructs a 4D knowledge database by anchoring object-level semantic descriptions in metric space and time, yielding a persistent world model that can be shared across agents. At inference, natural language queries are decomposed into semantic, spatial, and temporal keys to retrieve relevant observations, which are integrated into the VLM's reasoning. Unlike classical retrieval-augmented generation methods, retrieval in R4 operates directly in 4D space, enabling episodic and collaborative reasoning without training. Experiments on embodied question answering and navigation benchmarks demonstrate that R4 substantially improves retrieval and reasoning over spatio-temporal information compared to baselines, advancing a new paradigm for embodied 4D reasoning in dynamic environments.
Read the full abstract

All authors Tin Stribor Sohn, Maximilian Dillitzer, Jason J. Corso, Eric Sax

Robotics

Large Video Planner Enables Generalizable Robot Control

Boyuan Chen, Tianyuan Zhang, Haoran Geng et al. (+9 more)

General-purpose robots require decision-making models that generalize across diverse tasks and environments. Recent works build robot foundation models by extending multimodal large language models (MLLMs) with action outputs, creating vision-language-action (VLA) systems. These efforts are motivated by the intuition that MLLMs' large-scale language and image pretraining can be effectively transferred to the action output modality. In this work, we explore an alternative paradigm of using large-scale video pretraining as a primary modality for building robot foundation models. Unlike static images and language, videos capture spatio-temporal sequences of states and actions in the physical world that are naturally aligned with robotic behavior. We curate an internet-scale video dataset of human activities and task demonstrations, and train, for the first time at a foundation-model scale, an open video model for generative robotics planning. The model produces zero-shot video plans for novel scenes and tasks, which we post-process to extract executable robot actions. We evaluate task-level generalization through third-party selected tasks in the wild and real-robot experiments, demonstrating successful physical execution. Together, these results show robust instruction following, strong generalization, and real-world feasibility. We release both the model and dataset to support open, reproducible video-based robot learning. Our website is available at https://www.boyuan.space/large-video-planner/.
Read the full abstract

All authors Boyuan Chen, Tianyuan Zhang, Haoran Geng, Caiyi Zhang, Peihao Li, Kiwhan Song, William T. Freeman, Jitendra Malik, Pieter Abbeel, Russ Tedrake, Vincent Sitzmann, Yilun Du

Robotics

mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs

Jonas Pai, Liam Achenbach, Victoriano Montesinos et al. (+3 more)

Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected static web data. As a result, despite improved semantic generalization, the policy must implicitly infer complex physical dynamics and temporal dependencies solely from robot trajectories. This reliance creates an unsustainable data burden, necessitating continuous, large-scale expert data collection to compensate for the lack of innate physical understanding. We contend that while vision-language pretraining effectively captures semantic priors, it remains blind to physical causality. A more effective paradigm leverages video to jointly capture semantics and visual dynamics during pretraining, thereby isolating the remaining task of low-level control. To this end, we introduce mimic-video, a novel Video-Action Model (VAM) that pairs a pretrained Internet-scale video model with a flow matching-based action decoder conditioned on its latent representations. The decoder serves as an Inverse Dynamics Model (IDM), generating low-level robot actions from the latent representation of video-space action plans. Our extensive evaluation shows that our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.
Read the full abstract

All authors Jonas Pai, Liam Achenbach, Victoriano Montesinos, Benedek Forrai, Oier Mees, Elvis Nava

Robotics

An Open Toolkit for Underwater Field Robotics

Giacomo Picardi, Saverio Iacoponi, Matias Carandell et al. (+5 more)

Underwater robotics is becoming increasingly important for marine science, environmental monitoring, and subsea industrial operations, yet the development of underwater manipulation and actuation systems remains restricted by high costs, proprietary designs, and limited access to modular, research-oriented hardware. While open-source initiatives have democratized vehicle construction and control software, a substantial gap persists for joint-actuated systems-particularly those requiring waterproof, feedback-enabled actuation suitable for manipulators, grippers, and bioinspired devices. As a result, many research groups face lengthy development cycles, limited reproducibility, and difficulty transitioning laboratory prototypes to field-ready platforms. To address this gap, we introduce an open, cost-effective hardware and software toolkit for underwater manipulation research. The toolkit includes a depth-rated Underwater Robotic Joint (URJ) with early leakage detection, compact control and power management electronics, and a ROS2-based software stack for sensing and multi-mode actuation. All CAD models, fabrication files, PCB sources, firmware, and ROS2 packages are openly released, enabling local manufacturing, modification, and community-driven improvement. The toolkit has undergone extensive laboratory testing and multiple field deployments, demonstrating reliable operation up to 40 m depth across diverse applications, including a 3-DoF underwater manipulator, a tendon-driven soft gripper, and an underactuated sediment sampler. These results validate the robustness, versatility, and reusability of the toolkit for real marine environments. By providing a fully open, field-tested platform, this work aims to lower the barrier to entry for underwater manipulation research, improve reproducibility, and accelerate innovation in underwater field robotics.
Read the full abstract

All authors Giacomo Picardi, Saverio Iacoponi, Matias Carandell, Jorge Aguirregomezcorta, Mrudul Chellapurath, Joaquin del Rio, Marcello Calisti, Iacopo Aguzzi

Robotics

OMCL: Open-vocabulary Monte Carlo Localization

Evgenii Kruzhkov, Raphael Memmesheimer and Sven Behnke

Robust robot localization is an important prerequisite for navigation, but it becomes challenging when the map and robot measurements are obtained from different sensors. Prior methods are often tailored to specific environments, relying on closed-set semantics or fine-tuned features. In this work, we extend Monte Carlo Localization with vision-language features, allowing OMCL to robustly compute the likelihood of visual observations given a camera pose and a 3D map created from posed RGB-D images or aligned point clouds. These open-vocabulary features enable us to associate observations and map elements from different modalities, and to natively initialize global localization through natural language descriptions of nearby objects. We evaluate our approach using Matterport3D and Replica for indoor scenes and demonstrate generalization on SemanticKITTI for outdoor scenes.
Read the full abstract

Robotics · Cross-listed from quant-ph

QuantGraph: A Receding-Horizon Quantum Graph Solver

Pranav Vaidhyanathan, Aristotelis Papatheodorou, David R. M. Arvidsson-Shukur et al. (+3 more)

Dynamic programming is a cornerstone of graph-based optimization. While effective, it scales unfavorably with problem size. In this work, we present QuantGraph, a two-stage quantum-enhanced framework that casts local and global graph-optimization problems as quantum searches over discrete trajectory spaces. The solver is designed to operate efficiently by first finding a sequence of locally optimal transitions in the graph (local stage), without considering full trajectories. The accumulated cost of these transitions acts as a threshold that prunes the search space (up to 60% reduction for certain examples). The subsequent global stage, based on this threshold, refines the solution. Both stages utilize variants of the Grover-adaptive-search algorithm. To achieve scalability and robustness, we draw on principles from control theory and embed QuantGraph's global stage within a receding-horizon model-predictive-control scheme. This classical layer stabilizes and guides the quantum search, improving precision and reducing computational burden. In practice, the resulting closed-loop system exhibits robust behavior and lower overall complexity. Notably, for a fixed query budget, QuantGraph attains a 2x increase in control-discretization precision while still benefiting from Grover-search's inherent quadratic speedup compared to classical methods.
Read the full abstract

All authors Pranav Vaidhyanathan, Aristotelis Papatheodorou, David R. M. Arvidsson-Shukur, Mark T. Mitchison, Natalia Ares, Ioannis Havoutis

Robotics

Load-Based Variable Transmission Mechanism for Robotic Applications

Sinan Emre, Victor Barasuol, Matteo Villa et al. (+1 more)

This paper presents a Load-Based Variable Transmission (LBVT) mechanism designed to enhance robotic actuation by dynamically adjusting the transmission ratio in response to external torque demands. Unlike existing variable transmission systems that require additional actuators for active control, the proposed LBVT mechanism leverages a pre-tensioned spring and a four-bar linkage to passively modify the transmission ratio, thereby reducing the complexity of robot joint actuation systems. The effectiveness of the LBVT mechanism is evaluated through simulation-based analyses. The results confirm that the system achieves up to a 40 percent increase in transmission ratio upon reaching a predefined torque threshold, effectively amplifying joint torque when required without additional actuation. Furthermore, the simulations demonstrate a torque amplification effect triggered when the applied force exceeds 18 N, highlighting the system ability to autonomously respond to varying load conditions. This research contributes to the development of lightweight, efficient, and adaptive transmission systems for robotic applications, particularly in legged robots where dynamic torque adaptation is critical.
Read the full abstract

All authors Sinan Emre, Victor Barasuol, Matteo Villa, Claudio Semini

Robotics · Cross-listed from cs.CV

The 3D Mirage: Probing and Taming 3D Hallucinations

Hoang Nguyen, Xiaohao Xu and Xiaonan Huang

Monocular depth foundation models achieve remarkable generalization by learning large-scale semantic priors, but this creates a critical vulnerability: they hallucinate illusory 3D structures from planar/low-curvature but perceptually ambiguous inputs. We term this failure the 3D Mirage. This paper introduces a novel end-to-end framework to probe, score, and tame this under-quantified safety risk in monocular depth under context variation. To probe, we present 3D-Mirage, the first benchmark to combine context variation and precise annotation for real-world illusions with real object exclusions, multi-surface support; purpose-built to stress-test monocular depth on real-world illusions. To score, we propose a second-order magnitude-based evaluation with two metrics: the Deviation Composite Score (DCS) for high second-order 3D structure and the Confusion Composite Score (CCS) for contextual instability. To tame this failure, we introduce Grounded Self-Distillation, a parameter-efficient strategy on Depth-Anything-V2 baseline that surgically targets and resolves hallucination on illusion ROIs while preserving background knowledge, avoiding catastrophic forgetting. Our work provides an innovative pipeline for diagnosing and addressing this phenomenon, urging a necessary shift in the evaluation of MDE from pixel-wise accuracy to structural and contextual robustness.
Read the full abstract

Robotics

MiVLA: Towards Generalizable Vision-Language-Action Model with Human-Robot Mutual Imitation Pre-training

Zhenhan Yin, Xuanhan Wang, Jiahao Jiang et al. (+8 more)

While leveraging abundant human videos and simulated robot data poses a scalable solution to the scarcity of real-world robot data, the generalization capability of existing vision-language-action models (VLAs) remains limited by mismatches in camera views, visual appearance, and embodiment morphologies. To overcome this limitation, we propose MiVLA, a generalizable VLA empowered by human-robot mutual imitation pre-training, which leverages inherent behavioral similarity between human hands and robotic arms to build a foundation of strong behavioral priors for both human actions and robotic control. Specifically, our method utilizes kinematic rules with left/right hand coordinate systems for bidirectional alignment between human and robot action spaces. Given human or simulated robot demonstrations, MiVLA is trained to forecast behavior trajectories for one embodiment, and imitate behaviors for another one unseen in the demonstration. Based on this mutual imitation, it integrates the behavioral fidelity of real-world human data with the manipulative diversity of simulated robot data into a unified model, thereby enhancing the generalization capability for downstream tasks. Extensive experiments conducted on both simulation and real-world platforms with three robots (ARX, PiPer and LocoMan), demonstrate that MiVLA achieves strong improved generalization capability, outperforming state-of-the-art VLAs (e.g., $\boldsymbol{\pi}_{0}$, $\boldsymbol{\pi}_{0.5}$ and H-RDT) by 25% in simulation, and 14% in real-world robot control tasks.
Read the full abstract

All authors Zhenhan Yin, Xuanhan Wang, Jiahao Jiang, Kaiyuan Deng, Pengqi Chen, Shuangle Li, Chong Liu, Xing Xu, Jingkuan Song, Lianli Gao, Heng Tao Shen

Robotics

Remotely Detectable Robot Policy Watermarking

Michael Amir, Manon Flageat and Amanda Prorok

The success of machine learning for real-world robotic systems has created a new form of intellectual property: the trained policy. This raises a critical need for novel methods that verify ownership and detect unauthorized, possibly unsafe misuse. While watermarking is established in other domains, physical policies present a unique challenge: remote detection. Existing methods assume access to the robot's internal state, but auditors are often limited to external observations (e.g., video footage). This “Physical Observation Gap” means the watermark must be detected from signals that are noisy, asynchronous, and filtered by unknown system dynamics. We formalize this challenge using the concept of a glimpse sequence, and introduce Colored Noise Coherency (CoNoCo), the first watermarking strategy designed for remote detection. CoNoCo embeds a spectral signal into the robot's motions by leveraging the policy's inherent stochasticity. To show it does not degrade performance, we prove CoNoCo preserves the marginal action distribution. Our experiments demonstrate strong, robust detection across various remote modalities, including motion capture and side-way/top-down video footage, in both simulated and real-world robot experiments. This work provides a necessary step toward protecting intellectual property in robotics, offering the first method for validating the provenance of physical policies non-invasively, using purely remote observations.
Read the full abstract

Robotics

GuangMing-Explorer: A Four-Legged Robot Platform for Autonomous Exploration in General Environments

Kai Zhang, Shoubin Chen, Dong Li et al. (+5 more)

Autonomous exploration is a fundamental capability that tightly integrates perception, planning, control, and motion execution. It plays a critical role in a wide range of applications, including indoor target search, mapping of extreme environments, resource exploration, etc. Despite significant progress in individual components, a holistic and practical description of a completely autonomous exploration system, encompassing both hardware and software, remains scarce. In this paper, we present GuangMing-Explorer, a fully integrated autonomous exploration platform designed for robust operation across diverse environments. We provide a comprehensive overview of the system architecture, including hardware design, software stack, algorithm deployment, and experimental configuration. Extensive real-world experiments demonstrate the platform's effectiveness and efficiency in executing autonomous exploration tasks, highlighting its potential for practical deployment in complex and unstructured environments.
Read the full abstract

All authors Kai Zhang, Shoubin Chen, Dong Li, Baiyang Zhang, Tao Huang, Zehao Wu, Jiasheng Chen, Bo Zhang

Robotics

A Network-Based Framework for Modeling and Analyzing Human-Robot Coordination Strategies

Martijn IJtsma and Salvatore Hargis

Studies of human-robot interaction in dynamic and unstructured environments show that as more advanced robotic capabilities are deployed, the need for cooperative competencies to support collaboration with human problem-holders increases. Designing human-robot systems to meet these demands requires an explicit understanding of the work functions and constraints that shape the feasibility of alternative joint work strategies. Yet existing human-robot interaction frameworks either emphasize computational support for real-time execution or rely on static representations for design, offering limited support for reasoning about coordination dynamics during early-stage conceptual design. To address this gap, this article presents a novel computational framework for analyzing joint work strategies in human-robot systems by integrating techniques from functional modeling with graph-theoretic representations. The framework characterizes collective work in terms of the relationships among system functions and the physical and informational structure of the work environment, while explicitly capturing how coordination demands evolve over time. Its use during conceptual design is demonstrated through a case study in disaster robotics, which shows how the framework can be used to support early trade-space exploration of human-robot coordination strategies and to identify cooperative competencies that support flexible management of coordination overhead. These results show how the framework makes coordination demands and their temporal evolution explicit, supporting design-time reasoning about cooperative competency requirements and work demands prior to implementation.
Read the full abstract

Robotics

VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments

Yuze Wu, Mo Zhu, Xingxing Li et al. (+6 more)

This paper proposes VLA-AN, an efficient and onboard Vision-Language-Action (VLA) framework dedicated to autonomous drone navigation in complex environments. VLA-AN addresses four major limitations of existing large aerial navigation models: the data domain gap, insufficient temporal navigation with reasoning, safety issues with generative action policies, and onboard deployment constraints. First, we construct a high-fidelity dataset utilizing 3D Gaussian Splatting (3D-GS) to effectively bridge the domain gap. Second, we introduce a progressive three-stage training framework that sequentially reinforces scene comprehension, core flight skills, and complex navigation capabilities. Third, we design a lightweight, real-time action module coupled with geometric safety correction. This module ensures fast, collision-free, and stable command generation, mitigating the safety risks inherent in stochastic generative policies. Finally, through deep optimization of the onboard deployment pipeline, VLA-AN achieves a robust real-time 8.3x improvement in inference throughput on resource-constrained UAVs. Extensive experiments demonstrate that VLA-AN significantly improves spatial grounding, scene reasoning, and long-horizon navigation, achieving a maximum single-task success rate of 98.1%, and providing an efficient, practical solution for realizing full-chain closed-loop autonomy in lightweight aerial robots.
Read the full abstract

All authors Yuze Wu, Mo Zhu, Xingxing Li, Yuheng Du, Yuxin Fan, Wenjun Li, Zhichao Han, Xin Zhou, Fei Gao

Robotics

Infrastructure-based Autonomous Mobile Robots for Internal Logistics – Challenges and Future Perspectives

Erik Brorsson, Kristian Ceder, Ze Zhang et al. (+11 more)

The adoption of Autonomous Mobile Robots (AMRs) for internal logistics is accelerating, with most solutions emphasizing decentralized, onboard intelligence. While AMRs in indoor environments like factories can be supported by infrastructure, involving external sensors and computational resources, such systems remain underexplored in the literature. This paper presents a comprehensive overview of infrastructure-based AMR systems, outlining key opportunities and challenges. To support this, we introduce a reference architecture combining infrastructure-based sensing, on-premise cloud computing, and onboard autonomy. Based on the architecture, we review core technologies for localization, perception, and planning. We demonstrate the approach in a real-world deployment in a heavy-vehicle manufacturing environment and summarize findings from a user experience (UX) evaluation. Our aim is to provide a holistic foundation for future development of scalable, robust, and human-compatible AMR systems in complex industrial environments.
Read the full abstract

All authors Erik Brorsson, Kristian Ceder, Ze Zhang, Sabino Francesco Roselli, Endre Erős, Martin Dahl, Beatrice Alenljung, Jessica Lindblom, Thanh Bui, Emmanuel Dean, Lennart Svensson, Kristofer Bengtsson, Per-Lage Götvall, Knut Åkesson

Robotics

EPSM: A Novel Metric to Evaluate the Safety of Environmental Perception in Autonomous Driving

Jörg Gamerdinger, Sven Teufel, Stephan Amann et al. (+2 more)

Extensive evaluation of perception systems is crucial for ensuring the safety of intelligent vehicles in complex driving scenarios. Conventional performance metrics such as precision, recall and the F1-score assess the overall detection accuracy, but they do not consider the safety-relevant aspects of perception. Consequently, perception systems that achieve high scores in these metrics may still cause misdetections that could lead to severe accidents. Therefore, it is important to evaluate not only the overall performance of perception systems, but also their safety. We therefore introduce a novel safety metric for jointly evaluating the most critical perception tasks, object and lane detection. Our proposed framework integrates a new, lightweight object safety metric that quantifies the potential risk associated with object detection errors, as well as an lane safety metric including the interdependence between both tasks that can occur in safety evaluation. The resulting combined safety score provides a unified, interpretable measure of perception safety performance. Using the DeepAccident dataset, we demonstrate that our approach identifies safety critical perception errors that conventional performance metrics fail to capture. Our findings emphasize the importance of safety-centric evaluation methods for perception systems in autonomous driving.
Read the full abstract

All authors Jörg Gamerdinger, Sven Teufel, Stephan Amann, Lukas Marc Listl, Oliver Bringmann

Robotics · Cross-listed from cs.CV

Criticality Metrics for Relevance Classification in Safety Evaluation of Object Detection in Automated Driving

Jörg Gamerdinger, Sven Teufel, Stephan Amann et al. (+1 more)

Ensuring safety is the primary objective of automated driving, which necessitates a comprehensive and accurate perception of the environment. While numerous performance evaluation metrics exist for assessing perception capabilities, incorporating safety-specific metrics is essential to reliably evaluate object detection systems. A key component for safety evaluation is the ability to distinguish between relevant and non-relevant objects - a challenge addressed by criticality or relevance metrics. This paper presents the first in-depth analysis of criticality metrics for safety evaluation of object detection systems. Through a comprehensive review of existing literature, we identify and assess a range of applicable metrics. Their effectiveness is empirically validated using the DeepAccident dataset, which features a variety of safety-critical scenarios. To enhance evaluation accuracy, we propose two novel application strategies: bidirectional criticality rating and multi-metric aggregation. Our approach demonstrates up to a 100% improvement in terms of criticality classification accuracy, highlighting its potential to significantly advance the safety evaluation of object detection systems in automated vehicles.
Read the full abstract

All authors Jörg Gamerdinger, Sven Teufel, Stephan Amann, Oliver Bringmann

Robotics · Cross-listed from cs.HC

"I am here for you": How relational conversational AI appeals to adolescents, especially those who are socially and emotionally vulnerable

Pilyoung Kim, Yun Xie and Sujin Yang

General-purpose conversational AI chatbots and AI companions increasingly provide young adolescents with emotionally supportive conversations, raising questions about how conversational style shapes anthropomorphism and emotional reliance. In a preregistered online experiment with 284 adolescent-parent dyads, youth aged 11-15 and their parents read two matched transcripts in which a chatbot responded to an everyday social problem using either a relational style (first-person, affiliative, commitment language) or a transparent style (explicit nonhumanness, informational tone). Adolescents more often preferred the relational than the transparent style, whereas parents were more likely to prefer transparent style than adolescents. Adolescents rated the relational chatbot as more human-like, likable, trustworthy and emotionally close, while perceiving both styles as similarly helpful. Adolescents who preferred relational style had lower family and peer relationship quality and higher stress and anxiety than those preferring transparent style or both chatbots. These findings identify conversational style as a key design lever for youth AI safety, showing that relational framing heightens anthropomorphism, trust and emotional closeness and can be especially appealing to socially and emotionally vulnerable adolescents, who may be at increased risk for emotional reliance on conversational AI.
Read the full abstract

Robotics

BEV-Patch-PF: Particle Filtering with BEV-Aerial Feature Matching for Off-Road Geo-Localization

Dongmyeong Lee, Jesse Quattrociocchi, Christian Ellis et al. (+5 more)

We propose BEV-Patch-PF, a GPS-free sequential geo-localization system that integrates a particle filter with learned bird's-eye-view (BEV) and aerial feature maps. From onboard RGB and depth images, we construct a BEV feature map. For each 3-DoF particle pose hypothesis, we crop the corresponding patch from an aerial feature map computed from a local aerial image queried around the approximate location. BEV-Patch-PF computes a per-particle log-likelihood by matching the BEV feature to the aerial patch feature. On two real-world off-road datasets, our method achieves 9.7x lower absolute trajectory error (ATE) on seen routes and 6.6x lower ATE on unseen routes than a retrieval-based baseline, while maintaining accuracy under dense canopy and shadow. The system runs in real time at 10 Hz on an NVIDIA Tesla T4, enabling practical robot deployment.
Read the full abstract

All authors Dongmyeong Lee, Jesse Quattrociocchi, Christian Ellis, Rwik Rana, Amanda Adkins, Adam Uccello, Garrett Warnell, Joydeep Biswas

Robotics

NAP3D: NeRF Assisted 3D-3D Pose Alignment for Autonomous Vehicles

Gaurav Bansal

Accurate localization is essential for autonomous vehicles, yet sensor noise and drift over time can lead to significant pose estimation errors, particularly in long-horizon environments. A common strategy for correcting accumulated error is visual loop closure in SLAM, which adjusts the pose graph when the agent revisits previously mapped locations. These techniques typically rely on identifying visual mappings between the current view and previously observed scenes and often require fusing data from multiple sensors. In contrast, this work introduces NeRF-Assisted 3D-3D Pose Alignment (NAP3D), a complementary approach that leverages 3D-3D correspondences between the agent's current depth image and a pre-trained Neural Radiance Field (NeRF). By directly aligning 3D points from the observed scene with synthesized points from the NeRF, NAP3D refines the estimated pose even from novel viewpoints, without relying on revisiting previously observed locations. This robust 3D-3D formulation provides advantages over conventional 2D-3D localization methods while remaining comparable in accuracy and applicability. Experiments demonstrate that NAP3D achieves camera pose correction within 5 cm on a custom dataset, robustly outperforming a 2D-3D Perspective-N-Point baseline. On TUM RGB-D, NAP3D consistently improves 3D alignment RMSE by approximately 6 cm compared to this baseline given varying noise, despite PnP achieving lower raw rotation and translation parameter error in some regimes, highlighting NAP3D's improved geometric consistency in 3D space. By providing a lightweight, dataset-agnostic tool, NAP3D complements existing SLAM and localization pipelines when traditional loop closure is unavailable.
Read the full abstract

Robotics

HERO: Hierarchical Traversable 3D Scene Graphs for Embodied Navigation Among Movable Obstacles

Yunheng Wang, Yixiao Feng, Yuetong Fang et al. (+5 more)

3D Scene Graphs (3DSGs) constitute a powerful representation of the physical world, distinguished by their abilities to explicitly model the complex spatial, semantic, and functional relationships between entities, rendering a foundational understanding that enables agents to interact intelligently with their environment and execute versatile behaviors. Embodied navigation, as a crucial component of such capabilities, leverages the compact and expressive nature of 3DSGs to enable long-horizon reasoning and planning in complex, large-scale environments. However, prior works rely on a static-world assumption, defining traversable space solely based on static spatial layouts and thereby treating interactable obstacles as non-traversable. This fundamental limitation severely undermines their effectiveness in real-world scenarios, leading to limited reachability, low efficiency, and inferior extensibility. To address these issues, we propose HERO, a novel framework for constructing Hierarchical Traversable 3DSGs, that redefines traversability by modeling operable obstacles as pathways, capturing their physical interactivity, functional semantics, and the scene's relational hierarchy. The results show that, relative to its baseline, HERO reduces PL by 35.1% in partially obstructed environments and increases SR by 79.4% in fully obstructed ones, demonstrating substantially higher efficiency and reachability.
Read the full abstract

All authors Yunheng Wang, Yixiao Feng, Yuetong Fang, Shuning Zhang, Tan Jing, Jian Li, Xiangrui Jiang, Renjing Xu

Robotics

ISS Policy : Scalable Diffusion Policy with Implicit Scene Supervision

Wenlong Xia, Jinhao Zhang, Ce Zhang et al. (+6 more)

Vision-based imitation learning has enabled impressive robotic manipulation skills, but action imitation alone provides limited supervision of the geometric consequences of robot behavior. To address this limitation, we introduce **Implicit Scene Supervision (ISS) Policy**, a 3D visuomotor diffusion policy with a DiT backbone that predicts continuous action sequences from point-cloud observations. ISS augments action diffusion with a supervised robot motion predictor that maps generated actions and robot-state context to end-effector motion, and then uses the predicted motion together with gripper intent to forecast future point-cloud representations. By explicitly modeling the intermediate transition from action to robot motion, ISS encourages the policy to capture how its actions affect the surrounding 3D scene. We further introduce asymmetric gradient routing to separate direct motion regression from scene-level policy supervision, together with a change-balanced objective that accounts for variations in scene-change magnitude. These auxiliary objectives provide dynamics-aware geometric supervision using only expert demonstrations, without requiring additional annotations or auxiliary modules at inference time. ISS Policy achieves state-of-the-art performance on single-arm manipulation tasks in MetaWorld and dexterous manipulation tasks in Adroit, while real-world dual-arm experiments further demonstrate its effectiveness on physical robotic manipulation. The resulting framework preserves the scalable DiT backbone and standard diffusion-policy control interface. Code and videos will be released.
Read the full abstract

All authors Wenlong Xia, Jinhao Zhang, Ce Zhang, Yaojia Wang, Huizhe Li, Yichen Lai, Yude Li, Youmin Gong, Jie Mei

Tuesday 16 December

Robotics · Cross-listed from cs.HC

Social Robotics for Disabled Students: An Empirical Investigation of Embodiment, Roles and Interaction

Alva Markelius, Fethiye Irmak Doğan, Julie Bailey et al. (+3 more)

Institutional and social barriers in higher education often prevent students with disabilities from effectively accessing support, including lengthy procedures, insufficient information, and high social-emotional demands. This study empirically explores how disabled students perceive robot-based support, comparing two interaction roles, one information based (signposting) and one disclosure based (sounding board), and two embodiment types (physical robot/disembodied voice agent). Participants assessed these systems across five dimensions: perceived understanding, social energy demands, information access/clarity, task difficulty, and data privacy concerns. The main findings of the study reveal that the physical robot was perceived as more understanding than the voice-only agent, with embodiment significantly shaping perceptions of sociability, animacy, and privacy. We also analyse differences between disability types. These results provide critical insights into the potential of social robots to mitigate accessibility barriers in higher education, while highlighting ethical, social and technical challenges.
Read the full abstract

All authors Alva Markelius, Fethiye Irmak Doğan, Julie Bailey, Guy Laban, Jenny L. Gibson, Hatice Gunes

Robotics

Breathe with Me: Synchronizing Biosignals for User Embodiment in Robots

Iddo Yehoshua Wald, Amber Maimon, Shiyao Zhang et al. (+4 more)

Embodiment of users within robotic systems has been explored in human-robot interaction, most often in telepresence and teleoperation. In these applications, synchronized visuomotor feedback can evoke a sense of body ownership and agency, contributing to the experience of embodiment. We extend this work by employing embreathment, the representation of the user's own breath in real time, as a means for enhancing user embodiment experience in robots. In a within-subjects experiment, participants controlled a robotic arm, while its movements were either synchronized or non-synchronized with their own breath. Synchrony was shown to significantly increase body ownership, and was preferred by most participants. We propose the representation of physiological signals as a novel interoceptive pathway for human-robot interaction, and discuss implications for telepresence, prosthetics, collaboration with robots, and shared autonomy.
Read the full abstract

All authors Iddo Yehoshua Wald, Amber Maimon, Shiyao Zhang, Dennis Küster, Robert Porzel, Tanja Schultz, Rainer Malaka

Robotics · Cross-listed from cs.CV

CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives

Zihan Wang, Jiashun Wang, Jeff Tan et al. (+4 more)

We introduce CRISP, a method that recovers simulatable human motion and scene geometry from monocular video. Prior work on joint human-scene reconstruction relies on data-driven priors and joint optimization with no physics in the loop, or recovers noisy geometry with artifacts that cause motion tracking policies with scene interactions to fail. In contrast, our key insight is to recover convex, clean, and simulation-ready geometry by fitting planar primitives to a point cloud reconstruction of the scene, via a simple clustering pipeline over depth, normals, and flow. To reconstruct scene geometry that might be occluded during interactions, we make use of human-scene contact modeling (e.g., we use human posture to reconstruct the occluded seat of a chair). Finally, we ensure that human and scene reconstructions are physically-plausible by using them to drive a humanoid controller via reinforcement learning. Our approach reduces motion tracking failure rates from 55.2% to 6.9% on human-centric video benchmarks (EMDB, PROX), while delivering a 43% faster RL simulation throughput. We further validate it on in-the-wild videos including casually-captured videos, Internet videos, and even Sora-generated videos. This demonstrates CRISP's ability to generate physically-valid human motion and interaction environments at scale, greatly advancing real-to-sim applications for robotics and AR/VR.
Read the full abstract

All authors Zihan Wang, Jiashun Wang, Jeff Tan, Yiwen Zhao, Jessica Hodgins, Shubham Tulsiani, Deva Ramanan

Robotics

CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation

Sirui Chen, Zi-ang Cao, Zhengyi Luo et al. (+7 more)

Recent progress in humanoid robots has unlocked agile locomotion skills, including backflipping, running, and crawling. Yet it remains challenging for a humanoid robot to perform forceful manipulation tasks such as moving objects, wiping, and pushing a cart. We propose adaptive Compliance Humanoid control through hIsight Perturbation (CHIP), a plug-and-play module that enables controllable end-effector stiffness while preserving agile tracking of dynamic reference motions. CHIP is easy to implement and requires neither data augmentation nor additional reward tuning. We show that a generalist motion-tracking controller trained with CHIP can perform a diverse set of forceful manipulation tasks that require different end-effector compliance, such as multi-robot collaboration, wiping, box delivery, and door opening.
Read the full abstract

All authors Sirui Chen, Zi-ang Cao, Zhengyi Luo, Fernando Castañeda, Chenran Li, Tingwu Wang, Ye Yuan, Linxi "Jim" Fan, C. Karen Liu, Yuke Zhu

Robotics

EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models

Zechen Bai, Chen Gao and Mike Zheng Shou

Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through practice. Vision-Language-Action (VLA) models have advanced robotic manipulation by leveraging large language models, yet remain fundamentally limited by Supervised Finetuning (SFT): requiring hundreds of demonstrations per task, rigidly memorizing trajectories, and failing to adapt when deployment conditions deviate from training. We introduce EVOLVE-VLA, a test-time training framework enabling VLAs to continuously adapt through environment interaction with minimal or zero task-specific demonstrations. The key technical challenge is replacing oracle reward signals (unavailable at test time) with autonomous feedback. We address this through a learned progress estimator providing dense feedback, and critically, we design our framework to “tame” this inherently noisy signal via two mechanisms: (1) an accumulative progress estimation mechanism smoothing noisy point-wise estimates, and (2) a progressive horizon extension strategy enabling gradual policy evolution. EVOLVE-VLA achieves substantial gains: +8.6% on long-horizon tasks, +22.0% in 1-shot learning, and enables cross-task generalization – achieving 20.8% success on unseen tasks without task-specific demonstrations training (vs. 0% for pure SFT). Qualitative analysis reveals emergent capabilities absent in demonstrations, including error recovery and novel strategies. This work represents a critical step toward VLAs that truly learn and adapt, moving beyond static imitation toward continuous self-improvements.
Read the full abstract

Robotics · Cross-listed from eess.SY

Nonlinear System Identification Nano-drone Benchmark

Riccardo Busetto, Elia Cereda, Marco Forgione et al. (+3 more)

We introduce a benchmark for system identification based on 75k real-world samples from the Crazyflie 2.1 Brushless nano-quadrotor, a sub-50g aerial vehicle widely adopted in robotics research. The platform presents a challenging testbed due to its multi-input, multi-output nature, open-loop instability, and nonlinear dynamics under agile maneuvers. The dataset comprises four aggressive trajectories with synchronized 4-dimensional motor inputs and 13-dimensional output measurements. To enable fair comparison of identification methods, the benchmark includes a suite of multi-horizon prediction metrics for evaluating both one-step and multi-step error propagation. In addition to the data, we provide a detailed description of the platform and experimental setup, as well as baseline models highlighting the challenge of accurate prediction under real-world noise and actuation nonlinearities. All data, scripts, and reference implementations are released as open-source at https://github.com/idsia-robotics/nanodrone-sysid-benchmark to facilitate transparent comparison of algorithms and support research on agile, miniaturized aerial robotics.
Read the full abstract

All authors Riccardo Busetto, Elia Cereda, Marco Forgione, Gabriele Maroni, Dario Piga, Daniele Palossi

Robotics · Cross-listed from cs.CV

A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning

Zixin Zhang, Kanghao Chen, Hanqing Wang et al. (+5 more)

Affordance prediction, which identifies interaction regions on objects based on language instructions, is critical for embodied AI. Prevailing end-to-end models couple high-level reasoning and low-level grounding into a single monolithic pipeline and rely on training over annotated datasets, which leads to poor generalization on novel objects and unseen environments. In this paper, we move beyond this paradigm by proposing A4-Agent, a training-free agentic framework that decouples affordance prediction into a three-stage pipeline. Our framework coordinates specialized foundation models at test time: (1) a $\textbf{Dreamer}$ that employs generative models to visualize $\textit{how}$ an interaction would look; (2) a $\textbf{Thinker}$ that utilizes large vision-language models to decide $\textit{what}$ object part to interact with; and (3) a $\textbf{Spotter}$ that orchestrates vision foundation models to precisely locate $\textit{where}$ the interaction area is. By leveraging the complementary strengths of pre-trained models without any task-specific fine-tuning, our zero-shot framework significantly outperforms state-of-the-art supervised methods across multiple benchmarks and demonstrates robust generalization to real-world settings.
Read the full abstract

All authors Zixin Zhang, Kanghao Chen, Hanqing Wang, Hongfei Zhang, Harold Haodong Chen, Chenfei Liao, Litao Guo, Ying-Cong Chen

Robotics

Geometric Parameter Optimization of a Novel 3-(PP(2-(UPS))) Redundant Parallel Mechanism based on Workspace Determination

Quan Yuan, Daqian Cao and Weibang Bai

Redundant parallel robots are normally employed in scenarios requiring good precision, high load capability, and large workspace compared to traditional parallel mechanisms. However, the elementary robotic configuration and geometric parameter optimization are still quite challenging. This paper proposes a novel 3-(PP(2-(UPS))) redundant parallel mechanism, with good generalizability first, and further investigates the kinematic optimization issue by analyzing and investigating how its key geometric parameters influence the volume, shape, boundary completeness, and orientation capabilities of its workspace. The torsional capability index TI_1 and tilting capability index TI_2 are defined to evaluate the orientation performance of the mechanism. Numerical simulation studies are completed to indicate the analysis, providing reasonable but essential references for the parameter optimization of 3-(PP(2-(UPS))) and other similar redundant parallel mechanisms.
Read the full abstract

Robotics

Odyssey: An Automotive Lidar-Inertial Odometry Dataset with GNSS-denied situations

Aaron Kurda, Simon Steuernagel, Lukas Jung et al. (+1 more)

The development and evaluation of Lidar-Inertial Odometry (LIO) and Simultaneous Localization and Mapping (SLAM) systems requires a precise ground truth. The Global Navigation Satellite System (GNSS) is often used as a foundation for this, but its signals can be unreliable in obstructed environments due to multi-path effects or loss-of-signal. While existing datasets compensate for sporadic GNSS loss by incorporating Inertial Measurement Unit (IMU) measurements, the commonly used systems do not permit prolonged study of GNSS-denied environments due to accumulated drift. Therefore, the diversity of such datasets is limited. To close this gap, we present Odyssey, an automotive LIO dataset featuring: (1) a ground truth derived from a navigation-grade Ring Laser Gyroscope (RLG)-based RTK/INS, offering bias stability one to four orders of magnitude better than existing automotive datasets; (2) a comprehensive collection of 36 sequences across diverse environments, enabling robust and comprehensive evaluation and (3) prolonged GNSS-denied environments, including tunnels and, previously unseen in the context of automotive benchmarks, indoor parking garages. Here, our RLG-based system enables accurate evaluation in scenarios where commonly employed systems would drift excessively. Besides providing data for LIO, Odyssey also supports place recognition tasks through threefold trajectory repetition and integration of external mapping data via precise geodetic coordinates. All data, dataloader and supplementary material are available online at https://odyssey.uni-goettingen.de/ .
Read the full abstract

All authors Aaron Kurda, Simon Steuernagel, Lukas Jung, Marcus Baum