Robotics · Cross-listed from cs.MA
Logic-based Task Representation and Reward Shaping in Multiagent Reinforcement Learning
Nishant Doshi
This paper presents an approach for accelerated learning of optimal plans for a given task represented using Linear Temporal Logic (LTL) in multi-
agent systems. Given a set of options (temporally abstract actions) available to each
agent, we convert the task specification into the corresponding Buchi Automaton and proceed with a model-free approach which collects transition samples and constructs a product Semi Markov Decision Process (SMDP) on-the-fly. Value-based Reinforcement Learning
algorithms can then be used to synthesize a correct-by-design controller without learning the underlying transition model of the multi-
agent system. The exponential sample complexity due to multiple
agents is dealt with using a novel reward shaping approach. We test the proposed
algorithm in a deterministic gridworld simulation for different tasks and find that the reward shaping results in significant reduction in convergence times. We also infer that using options becomes increasing more relevant as the state and action space increases in multi-
agent systems.
Read the full abstract ▾
Robotics
Lagrange-Poincaré-Kepler Equations of Disturbed Space-Manipulator Systems in Orbit
Borna Monazzah Moghaddam and Robin Chhabra
This article presents an extension of the Lagrange-Poincare Equations (LPE) to model the dynamics of spacecraft-manipulator systems operating within a non-inertial orbital reference frame. Building upon prior formulations of LPE for vehicle-manipulator systems, the proposed framework, termed the Lagrange-Poincare-Kepler Equations (LPKE), incorporates the coupling between spacecraft attitude dynamics, orbital motion, and manipulator kinematics. The formalism combines the Euler-Poincare equations for the base spacecraft, Keplerian orbital dynamics for the reference frame, and reduced Euler-Lagrange equations for the manipulator's shape space, using an exponential joint parametrization. Leveraging the Lagrange-d'Alembert principle on principal bundles, we derive novel closed-form structural
matrices that explicitly capture the effects of orbital disturbances and their dynamic coupling with the manipulator system. The LPKE framework also systematically includes externally applied,
symmetry-breaking wrenches, allowing for immediate integration into hardware-in-the-loop simulations and model-based control architectures for autonomous robotic operations in the orbital environment. To illustrate the effectiveness of the proposed model and its numerical superiority, we present a simulation study analyzing orbital effects on a 7-degree-of-freedom manipulator mounted on a spacecraft.
Read the full abstract ▾
Robotics
RM-RL: Role-Model Reinforcement Learning for Precise Robot Manipulation
Xiangyu Chen, Chuhao Zhou, Yuxi Liu et al. (+1 more)
Precise
robot manipulation is critical for fine-grained applications such as chemical and biological experiments, where even small errors (e.g., reagent spillage) can invalidate an entire task. Existing approaches often rely on pre-collected expert demonstrations and train policies via imitation learning (IL) or offline reinforcement learning (RL). However, obtaining high-quality demonstrations for precision tasks is difficult and time-consuming, while offline RL commonly suffers from distribution shifts and low data efficiency. We introduce a Role-Model Reinforcement Learning (RM-RL) framework that unifies online and offline training in real-world environments. The key idea is a role-model strategy that automatically generates labels for online training data using approximately optimal actions, eliminating the need for human demonstrations. RM-RL reformulates policy learning as supervised training, reducing instability from distribution mismatch and improving efficiency. A hybrid training scheme further leverages online role-model data for offline reuse, enhancing data efficiency through repeated sampling. Extensive experiments show that RM-RL converges faster and more stably than existing RL methods, yielding significant gains in real-world manipulation: 53% improvement in translation accuracy and 20% in rotation accuracy. Finally, we demonstrate the successful execution of a challenging task, precisely placing a
cell plate onto a shelf, highlighting the framework's effectiveness where prior methods fail.
Read the full abstract ▾
All authors Xiangyu Chen, Chuhao Zhou, Yuxi Liu, Jianfei Yang
Robotics
Autonomous Reactive Masonry Construction using Collaborative Heterogeneous Aerial Robots with Experimental Demonstration
Marios-Nektarios Stamatopoulos, Elias Small, Shridhar Velhal et al. (+2 more)
This article presents a fully autonomous aerial masonry construction framework using heterogeneous unmanned aerial vehicles (
UAVs), supported by experimental validation. Two specialized
UAVs were developed for the task: (i) a brick-carrier
UAV equipped with a ball-joint actuation mechanism for precise brick manipulation, and (ii) an adhesion
UAV integrating a servo-controlled valve and extruder nozzle for accurate adhesion application. The proposed framework employs a reactive mission planning unit that combines a dependency graph of the construction layout with a conflict graph to manage simultaneous task execution, while hierarchical state machines ensure robust operation and safe transitions during task execution. Dynamic task allocation allows real-time adaptation to environmental feedback, while minimum-jerk trajectory generation ensures smooth and precise
UAV motion during brick pickup and placement. Additionally, the brick-carrier
UAV employs an onboard
vision system that estimates brick poses in real time using ArUco markers and a least-squares optimization filter, enabling accurate
alignment during construction. To the best of the authors' knowledge, this work represents the first experimental demonstration of fully autonomous aerial masonry construction using heterogeneous
UAVs, where one
UAV precisely places the bricks while another autonomously applies adhesion material between them. The experimental results supported by the
video showcase the effectiveness of the proposed framework and demonstrate its potential to serve as a foundation for future developments in autonomous aerial robotic construction.
Read the full abstract ▾
All authors Marios-Nektarios Stamatopoulos, Elias Small, Shridhar Velhal, Avijit Banerjee, George Nikolakopoulos
Robotics · Cross-listed from cs.CV
UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos
Mingxuan Liu, Honglin He, Elisa Ricci et al. (+2 more)
Urban
embodied AI
agents, ranging from delivery
robots to quadrupeds, are increasingly populating our cities, navigating chaotic streets to provide last-mile connectivity. Training such
agents requires diverse, high-fidelity urban environments to scale, yet existing human-crafted or procedurally generated simulation scenes either lack scalability or fail to capture real-world complexity. We introduce UrbanVerse, a data-driven real-to-sim system that converts crowd-sourced city-tour
videos into physics-aware, interactive simulation scenes. UrbanVerse consists of: (i) UrbanVerse-100K, a repository of 100k+ annotated urban 3D assets with semantic and physical attributes, and (ii) UrbanVerse-Gen, an automatic pipeline that extracts scene layouts from
video and instantiates metric-scale 3D simulations using retrieved assets. Running in IsaacSim, UrbanVerse offers 160 high-quality constructed scenes from 24 countries, along with a curated
benchmark of 10 artist-designed test scenes. Experiments show that UrbanVerse scenes preserve real-world semantics and layouts, achieving human-evaluated realism comparable to manually crafted scenes. In urban
navigation, policies trained in UrbanVerse exhibit scaling power laws and strong generalization, improving success by +6.3% in simulation and +30.1% in zero-shot sim-to-real transfer comparing to prior methods, accomplishing a 300 m real-world mission with only two interventions.
Read the full abstract ▾
All authors Mingxuan Liu, Honglin He, Elisa Ricci, Wayne Wu, Bolei Zhou
Robotics · Cross-listed from cs.CV
Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation
Shaowei Liu, Chuan Guo, Bing Zhou et al. (+1 more)
Close-proximity human-human interactive poses convey rich contextual information about interaction dynamics. Given such poses, humans can intuitively infer the context and anticipate possible past and future dynamics, drawing on strong priors of human behavior. Inspired by this observation, we propose Ponimator, a simple framework anchored on proximal interactive poses for versatile interaction animation. Our training data consists of close-contact two-person poses and their surrounding temporal context from motion-capture interaction
datasets. Leveraging interactive pose priors, Ponimator employs two conditional
diffusion models: (1) a pose animator that uses the temporal prior to generate dynamic motion sequences from interactive poses, and (2) a pose generator that applies the spatial prior to synthesize interactive poses from a single pose, text, or both when interactive poses are unavailable. Collectively, Ponimator supports diverse tasks, including image-based interaction animation, reaction animation, and text-to-interaction synthesis, facilitating the transfer of interaction knowledge from high-quality mocap data to open-world scenarios. Empirical experiments across diverse
datasets and applications demonstrate the universality of the pose prior and the effectiveness and robustness of our framework.
Read the full abstract ▾
All authors Shaowei Liu, Chuan Guo, Bing Zhou, Jian Wang
Robotics
RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks
Mingxuan Yan, Yuping Wang, Zechun Liu et al. (+1 more)
To tackle long-horizon tasks, recent hierarchical
vision-
language-action (VLAs) frameworks employ
vision-
language model (VLM)-based planners to decompose complex manipulation tasks into simpler sub-tasks that low-level visuomotor policies can easily handle. Typically, the VLM planner is finetuned to learn to decompose a target task. This finetuning requires target task demonstrations segmented into sub-tasks by either human annotation or heuristic rules. However, the heuristic subtasks can deviate significantly from the training data of the visuomotor policy, which degrades task performance. To address these issues, we propose a
Retrieval-based Demonstration Decomposer (RDD) that automatically decomposes demonstrations into sub-tasks by aligning the visual features of the decomposed sub-task intervals with those from the training data of the low-level visuomotor policies. Our method outperforms the state-of-the-art sub-task decomposer on both simulation and real-world tasks, demonstrating robustness across diverse settings. Code and more results are available at rdd-neurips.github.io.
Read the full abstract ▾
All authors Mingxuan Yan, Yuping Wang, Zechun Liu, Jiachen Li
Robotics
CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions
Lizhi Yang, Blake Werner, Massimiliano de Sa et al. (+1 more)
Reinforcement learning (RL), while powerful and expressive, can often prioritize performance at the expense of safety. Yet safety violations can lead to catastrophic outcomes in real-world deployments. Control Barrier Functions (CBFs) offer a principled method to enforce dynamic safety – traditionally deployed online via safety filters. While the result is safe behavior, the fact that the RL policy does not have knowledge of the CBF can lead to conservative behaviors. This paper proposes CBF-RL, a framework for generating safe behaviors with RL by enforcing CBFs in training. CBF-RL has two key attributes: (1) minimally modifying a nominal RL policy to encode safety constraints via a CBF term, (2) and safety filtering of the policy rollouts in training. Theoretically, we prove that continuous-time safety filters can be deployed via closed-form expressions on discrete-time roll-outs. Practically, we demonstrate that CBF-RL internalizes the safety constraints in the learned policy – both enforcing safer actions and biasing towards safer rewards – enabling safe deployment without the need for an online safety filter. We validate our framework through ablation studies on
navigation tasks and on the Unitree G1
humanoid robot, where CBF-RL enables safer exploration, faster convergence, and robust performance under uncertainty, enabling the
humanoid robot to avoid obstacles and climb stairs safely in real-world settings without a runtime safety filter.
Read the full abstract ▾
All authors Lizhi Yang, Blake Werner, Massimiliano de Sa, Aaron D. Ames
Robotics
From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance
Zhe Li, Cheng Chi, Yangyang Wei et al. (+7 more)
Natural
language offers a natural interface for
humanoid robots, but existing
language-guided
humanoid locomotion pipelines remain cumbersome and untrustworthy. They typically decode human motion, retarget it to
robot morphology, and then track it with a physics-based controller. However, this multi-stage process is prone to cumulative errors, introduces high latency, and yields weak coupling between semantics and control. These limitations call for a more direct pathway from
language to action, one that eliminates fragile intermediate stages. Therefore, we present RoboGhost, a retargeting-free framework that directly conditions
humanoid policies on
language-grounded motion latents. By bypassing explicit motion decoding and retargeting, RoboGhost enables a
diffusion-based policy to denoise executable actions directly from noise, preserving semantic intent and supporting fast, reactive control. A hybrid causal
transformer-
diffusion motion generator further ensures long-horizon consistency while maintaining stability and diversity, yielding rich latent representations for precise
humanoid behavior. Extensive experiments demonstrate that RoboGhost substantially reduces deployment latency, improves success rates and tracking precision, and produces smooth, semantically aligned locomotion on real
humanoids. Beyond text, the framework naturally extends to other modalities such as images, audio, and music, providing a universal foundation for
vision-
language-action
humanoid systems.
Read the full abstract ▾
All authors Zhe Li, Cheng Chi, Yangyang Wei, Boan Zhu, Yibo Peng, Tao Huang, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang, Chang Xu
Robotics
Architecture Is All You Need: Diversity-Enabled Sweet Spots for Robust Humanoid Locomotion
Blake Werner, Lizhi Yang and Aaron D. Ames
Robust
humanoid locomotion in unstructured environments requires architectures that balance fast low-level stabilization with slower perceptual decision-making. We show that a simple layered control architecture (LCA), a proprioceptive stabilizer running at high rate, coupled with a compact low-rate perceptual policy, enables substantially more robust performance than monolithic end-to-end designs, even when using minimal perception encoders. Through a two-stage training curriculum (blind stabilizer pretraining followed by perceptual fine-tuning), we demonstrate that layered policies consistently outperform one-stage alternatives in both simulation and hardware. On a Unitree G1
humanoid, our approach succeeds across stair and ledge tasks where one-stage perceptual policies fail. These results highlight that architectural separation of timescales, rather than network scale or complexity, is the key enabler for robust perception-conditioned locomotion.
Read the full abstract ▾
Robotics · Cross-listed from eess.IV
EdgeNavMamba: Mamba Optimized Object Detection for Energy Efficient Edge Devices
Romina Aalishah, Mozhgan Navardi and Tinoosh Mohsenin
Deployment of efficient and accurate Deep Learning models has long been a challenge in autonomous
navigation, particularly for real-time applications on resource-constrained edge devices. Edge devices are limited in computing power and
memory, making model efficiency and compression essential. In this work, we propose EdgeNavMamba, a reinforcement learning-based framework for goal-directed
navigation using an efficient Mamba object detection model. To train and evaluate the detector, we introduce a custom shape detection
dataset collected in diverse indoor settings, reflecting visual cues common in real-world
navigation. The object detector serves as a pre-processing module, extracting bounding boxes (BBOX) from visual input, which are then passed to an RL policy to control goal-oriented
navigation. Experimental results show that the student model achieved a reduction of 67% in size, and up to 73% in energy per inference on edge devices of NVIDIA Jetson Orin Nano and Raspberry Pi 5, while keeping the same performance as the teacher model. EdgeNavMamba also maintains high detection accuracy in MiniWorld and IsaacLab simulators while reducing parameters by 31% compared to the baseline. In the MiniWorld simulator, the
navigation policy achieves over 90% success across environments of varying complexity.
Read the full abstract ▾
Robotics
VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning
Binghao Huang, Jie Xu, Iretiayo Akinola et al. (+8 more)
Humans excel at bimanual assembly tasks by adapting to rich tactile feedback – a capability that remains difficult to replicate in
robots through behavioral cloning alone, due to the suboptimality and limited diversity of human demonstrations. In this work, we present VT-Refine, a visuo-tactile policy learning framework that combines real-world demonstrations, high-fidelity tactile simulation, and reinforcement learning to tackle precise, contact-rich bimanual assembly. We begin by training a
diffusion policy on a small set of demonstrations using synchronized visual and tactile inputs. This policy is then transferred to a simulated digital twin equipped with simulated tactile sensors and further refined via large-scale reinforcement learning to enhance robustness and generalization. To enable accurate sim-to-real transfer, we leverage high-resolution piezoresistive tactile sensors that provide normal force signals and can be realistically modeled in parallel using GPU-accelerated simulation. Experimental results show that VT-Refine improves assembly performance in both simulation and the real world by increasing data diversity and enabling more effective policy fine-tuning. Our project page is available at https://binghao-huang.github.io/vt_refine/.
Read the full abstract ▾
All authors Binghao Huang, Jie Xu, Iretiayo Akinola, Wei Yang, Balakumar Sundaralingam, Rowland O'Flaherty, Dieter Fox, Xiaolong Wang, Arsalan Mousavian, Yu-Wei Chao, Yunzhu Li
Robotics · Cross-listed from cs.HC
Design of Paper Robot Building Kits
Ruhan Yang and Ellen Yi-Luen Do
Building
robots is an engaging activity that provides opportunities for hands-on learning. However, traditional
robot-building kits are usually costly with limited functionality due to material and technology constraints. To improve the accessibility and flexibility of such kits, we take paper as the building material and extensively explore the versatility of paper-based interactions. Based on an analysis of current
robot-building kits and paper-based interaction research, we propose a design space for devising paper
robots. We also analyzed our building kit designs using this design space, where these kits demonstrate the potential of paper as a cost-effective material for
robot building. As a starting point, our design space and building kit examples provide a guideline that inspires and informs future research and development of novel paper
robot-building kits.
Read the full abstract ▾
Robotics
VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation
Han Zhao, Jiaxuan Zhang, Wenxuan Song et al. (+2 more)
Current
vision-
language-action (VLA) models, pre-trained on large-scale robotic data, exhibit strong multi-task capabilities and generalize well to variations in visual and
language instructions for manipulation. However, their success rate drops significantly when faced with object concepts outside the training data, such as unseen object descriptions and textures in the
dataset. To address this, we propose a novel agentic framework, VLA^2, which leverages OpenVLA as the execution backbone and effectively leverages external modules such as web
retrieval and object detection to provide visual and textual knowledge about target objects to the VLA. This approach mitigates generalization failure when handling out-of-distribution objects. Based on the LIBERO simulation environment, we introduced novel objects and object descriptions to construct a new evaluation
benchmark with three difficulty levels to test the effectiveness of our method. Our framework successfully outperformed the current state-of-the-art models on our designed hard-level generalization
benchmark. Compared to the standalone OpenVLA baseline, VLA^2 achieves a 44.2% improvement in the success rate in the hard-level
benchmark and an average improvement of 20.2% in all customized environments without any performance degradation on in-domain tasks. Project website: https://vla-2.github.io.
Read the full abstract ▾
All authors Han Zhao, Jiaxuan Zhang, Wenxuan Song, Pengxiang Ding, Donglin Wang
Robotics
STITCHER: Constrained Trajectory Planning in Complex Environments with Real-Time Motion Primitive Search
Helene J. Levy and Brett T. Lopez
Autonomous high-speed
navigation through large, complex environments requires real-time generation of agile trajectories that are dynamically feasible, collision-free, and satisfy state or actuator constraints. Modern trajectory planning techniques primarily use numerical optimization, as they enable the systematic computation of high-quality, expressive trajectories that satisfy various constraints. However, stringent requirements on computation time and the risk of numerical instability can limit the use of optimization-based planners in safety-critical scenarios. This work presents an optimization-free planning framework called STITCHER that stitches short trajectory segments together with graph search to compute long-range, expressive, and near-optimal trajectories in real-time. STITCHER outperforms modern optimization-based planners through our innovative planning architecture and several algorithmic developments that make real-time planning possible. Extensive simulation testing is performed to analyze the algorithmic components that make up STITCHER, along with a thorough comparison with three state-of-the-art optimization planners. Simulation tests show that safe trajectories can be created within a few milliseconds for paths that span the entirety of two 50 m x 50 m environments. Hardware tests with a custom quadrotor verify that STITCHER can produce trackable paths in real-time while respecting nonconvex constraints, such as limits on tilt angle and motor forces, with flight speeds up to 63 km/h.
Read the full abstract ▾
Robotics
SADCHER: Scheduling using Attention-based Dynamic Coalitions of Heterogeneous Robots in Real-Time
Jakob Bichler, Andreu Matoses Gimenez and Javier Alonso-Mora
We present Sadcher, a real-time task assignment framework for heterogeneous multi-
robot teams that incorporates dynamic coalition formation and task precedence constraints. Sadcher is trained through Imitation Learning and combines graph
attention and
transformers to predict assignment rewards between
robots and tasks. Based on the predicted rewards, a relaxed bipartite matching step generates high-quality schedules with feasibility guarantees. We explicitly model
robot and task positions, task durations, and
robots' remaining processing times, enabling advanced temporal and spatial
reasoning and generalization to environments with different spatiotemporal distributions compared to training. Trained on optimally solved small-scale instances, our method can scale to larger task sets and team sizes. Sadcher outperforms other learning-based and heuristic baselines on randomized, unseen problems for small and medium-sized teams with computation times suitable for real-time operation. We also explore sampling-based variants and evaluate scalability across
robot and task counts. In addition, we release our
dataset of 250,000 optimal schedules: https://autonomousrobots.nl/paper_websites/sadcher_MRTA/
Read the full abstract ▾
Robotics
Multi Agent Switching Mode Controller for Sound Source localization
Marcello Sorge, Nicola Cigarini, Riccardo Lorigiola et al. (+4 more)
Source seeking is an important topic in robotic research, especially considering sound-based sensors since they allow the
agents to locate a target even in critical conditions where it is not possible to establish a direct line of sight. In this work, we design a multi-
agent switching mode control strategy for acoustic-based target localization. Two scenarios are considered: single source localization, in which the
agents are driven maintaining a rigid formation towards the target, and multi-source scenario, in which each
agent searches for the targets independently from the others.
Read the full abstract ▾
All authors Marcello Sorge, Nicola Cigarini, Riccardo Lorigiola, Giulia Michieletto, Andrea Masiero, Angelo Cenedese, Alberto Guarnieri
Robotics · Cross-listed from cs.CV
QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models
Yixuan Li, Yuhui Chen, Mingcai Zhou et al. (+3 more)
Spatial perception and
reasoning are crucial for
Vision-
Language-Action (VLA) models to accomplish fine-grained manipulation tasks. However, existing approaches often lack the ability to understand and reason over the essential 3D structures necessary for precise control. To address this limitation, we propose QDepth-VLA, a general framework that augments VLA models with an auxiliary depth prediction task. A dedicated depth expert is designed to predict quantized latent
tokens of depth maps obtained from a VQ-VAE encoder, enabling the model to learn depth-aware representations that capture critical
geometric cues. Experimental results on the simulation
benchmarks and real-world tasks demonstrate that QDepth-VLA yields strong spatial
reasoning and competitive performance on manipulation tasks.
Read the full abstract ▾
All authors Yixuan Li, Yuhui Chen, Mingcai Zhou, Haoran Li, Zhengtao Zhang, Dongbin Zhao
Robotics
RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning
Kun Lei, Huanyu Li, Dongjie Yu et al. (+6 more)
Real-world robotic manipulation in homes and factories demands reliability, efficiency, and robustness that approach or surpass those of skilled human operators. We present RL-100, a real-world reinforcement learning framework built on
diffusion visuomotor policies. RL-100 unifies imitation and reinforcement learning under a single clipped PPO surrogate objective applied within the denoising process, yielding conservative and stable improvements across offline and online stages. To meet deployment latency requirements, a lightweight consistency
distillation method compresses multi-step
diffusion into a one-step controller for high-frequency control. The framework is task-, embodiment-, and representation-agnostic, and supports both single-action and action-chunking control. We evaluate RL-100 on eight diverse real-
robot tasks, from dynamic pushing and agile bowling to pouring, cloth folding, unscrewing, multi-stage juicing, and long-horizon box folding. RL-100 attains 100 percent success across evaluated trials, for a total of 1000 out of 1000 episodes, including up to 250 out of 250 consecutive trials on one task. It matches or surpasses expert teleoperators in time to completion. Without retraining, a single policy attains approximately 90 percent zero-shot success under environmental and dynamics shifts, adapts in a few-shot regime to significant task variations (86.7 percent), and remains robust to aggressive human perturbations (about 96 percent). Notably, our juicing
robot served random customers continuously for about seven hours without failure when deployed zero-shot in a shopping mall. These results suggest a practical path to deployment-ready
robot learning by starting from human priors, aligning training objectives with human-grounded metrics, and reliably extending performance beyond human demonstrations.
Read the full abstract ▾
All authors Kun Lei, Huanyu Li, Dongjie Yu, Zhenyu Wei, Lingxiao Guo, Zhennan Jiang, Ziyu Wang, Shiyu Liang, Huazhe Xu
Robotics · Cross-listed from cs.AI
RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning
Jinrui Liu, Bingyan Nie, Boyu Li et al. (+4 more)
Improving the
reasoning capabilities of
embodied agents is crucial for
robots to complete complex human instructions in long-view manipulation tasks successfully. Despite the success of large
language models and
vision language models based on Supervised Fine-Tuning (SFT) in planning tasks, they continue facing challenges in performing long-horizon manipulation tasks in complex real-world environments, owing to their restricted common sense and
reasoning capabilities. Considering that aligning general-purpose
vision language models to robotic planning tasks via supervised fine-tuning suffers from poor generalization and insufficient physical understanding, we propose RoboGPT-R1, a two-stage fine-tuning framework for
embodied planning. In this framework, supervised training acquires foundational knowledge through expert sequences, followed by RL to address the model's shortcomings in visual-spatial understanding and
reasoning. To achieve physical understanding and action sequence consistency in multi-step
reasoning tasks, we design a rule-based reward function that simultaneously considers long-horizon performance and action constraint in the environment. The
reasoning model, trained on Qwen2.5-VL-3B, significantly outperforms the larger-scale model, GPT-4o-mini, by 21.33% and surpasses other work trained on Qwen2.5-VL-7B by 20.33% on the EmbodiedBench
benchmark.
Read the full abstract ▾
All authors Jinrui Liu, Bingyan Nie, Boyu Li, Yaran Chen, Yuze Wang, Shunsen He, Haoran Li
Robotics
NeMo-map: Neural Implicit Flow Fields for Spatio-Temporal Motion Mapping
Yufei Zhu, Shih-Min Yang, Andrey Rudenko et al. (+3 more)
Safe and efficient
robot operation in complex human environments can benefit from good models of site-specific motion patterns. Maps of Dynamics (MoDs) provide such models by encoding statistical motion patterns in a map, but existing representations use discrete spatial sampling and typically require costly offline construction. We propose a continuous spatio-temporal MoD representation based on implicit neural functions that directly map coordinates to the parameters of a Semi-Wrapped Gaussian Mixture Model. This removes the need for discretization and imputation for unevenly sampled regions, enabling smooth generalization across both space and time. Evaluated on two public
datasets with real-world people tracking data, our method achieves better accuracy of motion representation and smoother velocity distributions in sparse regions while still being computationally efficient, compared to available baselines. The proposed approach demonstrates a powerful and efficient way of modeling complex human motion patterns and high performance in the trajectory prediction downstream task. The code is publicly available at https://github.com/test-bai-cpu/nemo-map.
Read the full abstract ▾
All authors Yufei Zhu, Shih-Min Yang, Andrey Rudenko, Tomasz P. Kucner, Achim J. Lilienthal, Martin Magnusson
Robotics
SkyDreamer: Interpretable End-to-End Vision-Based Drone Racing with Model-Based Reinforcement Learning
Aderik Verraest, Stavrow Bahnam, Robin Ferede et al. (+2 more)
Autonomous drone racing (ADR) systems have recently achieved champion-level performance, yet remain highly specific to drone racing. While end-to-end
vision-based methods promise broader applicability, no system to date simultaneously achieves full sim-to-real transfer, onboard execution, and champion-level performance. In this work, we present SkyDreamer, to the best of our knowledge, the first end-to-end
vision-based ADR policy that maps directly from pixel-level representations to motor commands. SkyDreamer builds on informed Dreamer, a model-based reinforcement learning approach where the world model decodes to privileged information only available during training. By extending this concept to end-to-end
vision-based ADR, the world model effectively functions as an implicit state and parameter
estimator, greatly improving interpretability. SkyDreamer runs fully onboard without external aid, resolves visual ambiguities by tracking progress using the state decoded from the world model's hidden state, and requires no extrinsic camera calibration, enabling rapid deployment across different drones without retraining. Real-world experiments show that SkyDreamer achieves robust, high-speed flight, executing tight maneuvers such as an inverted loop, a split-S and a ladder, reaching speeds of up to 21 m/s and accelerations of up to 6 g. It further demonstrates a non-trivial visual sim-to-real transfer by operating on poor-quality
segmentation masks, and exhibits robustness to battery depletion by accurately estimating the maximum attainable motor RPM and adjusting its flight path in real-time. These results highlight SkyDreamer's adaptability to important aspects of the reality gap, bringing robustness while still achieving extremely high-speed, agile flight.
Read the full abstract ▾
All authors Aderik Verraest, Stavrow Bahnam, Robin Ferede, Guido de Croon, Christophe De Wagter
Robotics
Open TeleDex: A Hardware-Agnostic Teleoperation System for Imitation Learning based Dexterous Manipulation
Xu Chi, Chao Zhang, Yang Su et al. (+7 more)
Accurate and high-fidelity demonstration data acquisition is a critical bottleneck for deploying
robot Imitation Learning (IL) systems, particularly when dealing with heterogeneous robotic platforms. Existing teleoperation systems often fail to guarantee high-precision data collection across diverse types of teleoperation devices. To address this, we developed Open TeleDex, a unified teleoperation framework engineered for demonstration data collection. Open TeleDex specifically tackles the TripleAny challenge, seamlessly supporting any robotic arm, any dexterous hand, and any external input device. Furthermore, we propose a novel hand pose retargeting
algorithm that significantly boosts the interoperability of Open TeleDex, enabling robust and accurate compatibility with an even wider spectrum of heterogeneous master and slave equipment. Open TeleDex establishes a foundational, high-quality, and publicly available platform for accelerating both academic research and industry development in complex robotic manipulation and IL.
Read the full abstract ▾
All authors Xu Chi, Chao Zhang, Yang Su, Lingfeng Dou, Fujia Yang, Jiakuo Zhao, Haoyu Zhou, Xiaoyou Jia, Yong Zhou, Shan An
Robotics
CADRE: Dynamic Catching via Implicit Contact Descriptors and Task-Appropriate Recovery Affordances
Fan Yang, Zixuan Huang, Abhinav Kumar et al. (+4 more)
Real-world dexterous manipulation often encounters unexpected errors and disturbances, which can lead to catastrophic failures, such as dropping the manipulated object. To address this challenge, we focus on the problem of catching a falling object while it remains within grasping range and, importantly, resetting the system to a configuration favorable for resuming the primary manipulation task. We propose Contact-Aware Dynamic Recovery (CADRE), a reinforcement learning framework that incorporates a Neural Descriptor Field (NDF)-inspired module to extract implicit contact features. Building on these contact features, we introduce an Implicit Recovery Affordance function to encourage recovery to task-appropriate states. Compared to methods that rely solely on object pose or point cloud input, NDFs can directly reason about finger-object correspondence and better establish a recovery target for RL training. Our experiments show that incorporating contact features improves training efficiency, enhances convergence performance for RL training, and ultimately leads to more successful recoveries. Additionally, we demonstrate that CADRE can generalize zero-shot to unseen objects with different geometries.
Read the full abstract ▾
All authors Fan Yang, Zixuan Huang, Abhinav Kumar, Sergio Aguilera Marinovic, Soshi Iba, Rana Soltani Zarrin, Dmitry Berenson
Robotics
When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks
Steffen Hagedorn, Luka Donkov, Aron Distelzweig et al. (+1 more)
Planner evaluation in closed-loop simulation often uses rule-based traffic
agents, whose simplistic and passive behavior can hide planner deficiencies and bias rankings. Widely used IDM
agents simply follow a lead vehicle and cannot react to vehicles in adjacent lanes, hindering tests of complex interaction capabilities. We address this issue by integrating the state-of-the-art learned traffic
agent model SMART into nuPlan. Thus, we are the first to evaluate planners under more realistic conditions and quantify how conclusions shift when narrowing the sim-to-real gap. Our analysis covers 14 recent planners and established baselines and shows that IDM-based simulation overestimates planning performance: nearly all scores deteriorate. In contrast, many planners interact better than previously assumed and even improve in multi-lane, interaction-heavy scenarios like lane changes or turns. Methods trained in closed-loop demonstrate the best and most stable driving performance. However, when reaching their limits in augmented edge-case scenarios, all learned planners degrade abruptly, whereas rule-based planners maintain reasonable basic behavior. Based on our results, we suggest SMART-reactive simulation as a new standard closed-loop
benchmark in nuPlan and release the SMART
agents as a drop-in alternative to IDM at https://github.com/shgd95/InteractiveClosedLoop.
Read the full abstract ▾
All authors Steffen Hagedorn, Luka Donkov, Aron Distelzweig, Alexandru P. Condurache
Robotics · Cross-listed from cs.SE
Requirement Identification for Traffic Simulations in Driving Simulators
Sven Tarlowski and Lutz Eckstein
This paper addresses the challenge of ensuring realistic traffic conditions by proposing a methodology that systematically identifies traffic simulation requirements. Using a structured approach based on sub-goals in each study phase, specific technical needs are derived for microscopic levels,
agent models, and visual representation. The methodology aims to maintain a high degree of fidelity, enhancing both the validity of experimental outcomes and participant engagement. By providing a clear link between study objectives and traffic simulation design, this approach supports robust automotive development and testing.
Read the full abstract ▾
Robotics
Spatially anchored Tactile Awareness for Robust Dexterous Manipulation
Jialei Huang, Yang Ye, Yuanqing Gong et al. (+3 more)
Dexterous manipulation requires precise
geometric reasoning, yet existing visuo-tactile learning methods struggle with sub-millimeter precision tasks that are routine for traditional model-based approaches. We identify a key limitation: while tactile sensors provide rich contact information, current learning frameworks fail to effectively leverage both the perceptual richness of tactile signals and their spatial relationship with hand kinematics. We believe an ideal tactile representation should explicitly ground contact measurements in a stable reference frame while preserving detailed sensory information, enabling policies to not only detect contact occurrence but also precisely infer object geometry in the hand's coordinate system. We introduce SaTA (Spatially-anchored Tactile Awareness for dexterous manipulation), an end-to-end policy framework that explicitly anchors tactile features to the hand's kinematic frame through forward kinematics, enabling accurate
geometric reasoning without requiring object models or explicit pose estimation. Our key insight is that spatially grounded tactile representations allow policies to not only detect contact occurrence but also precisely infer object geometry in the hand's coordinate system. We validate SaTA on challenging dexterous manipulation tasks, including bimanual USB-C mating in free space, a task demanding sub-millimeter
alignment precision, as well as light bulb installation requiring precise thread engagement and rotational control, and card sliding that demands delicate force modulation and angular precision. These tasks represent significant challenges for learning-based methods due to their stringent precision requirements. Across multiple
benchmarks, SaTA significantly outperforms strong visuo-tactile baselines, improving success rates by up to 30 percentage while reducing task completion times by 27 percentage.
Read the full abstract ▾
All authors Jialei Huang, Yang Ye, Yuanqing Gong, Xuezhou Zhu, Yang Gao, Kaifeng Zhang
Robotics
Generative Models From and For Sampling-Based MPC: A Bootstrapped Approach For Adaptive Contact-Rich Manipulation
Lara Brudermüller, Brandon Hung, Xinghao Zhu et al. (+4 more)
We present a generative predictive control (GPC) framework that amortizes sampling-based Model Predictive Control (SPC) by bootstrapping it with conditional flow-matching models trained on SPC control sequences collected in simulation. Unlike prior work relying on iterative refinement or gradient-based solvers, we show that meaningful proposal distributions can be learned directly from noisy SPC data, enabling more efficient and informed sampling during online planning. We further demonstrate, for the first time, the application of this approach to real-world contact-rich loco-manipulation with a quadruped
robot. Extensive experiments in simulation and on hardware show that our method improves sample efficiency, reduces planning horizon requirements, and generalizes robustly across task variations.
Read the full abstract ▾
All authors Lara Brudermüller, Brandon Hung, Xinghao Zhu, Jiuguang Wang, Nick Hawes, Preston Culbertson, Simon Le Cleac'h
Robotics
GOPLA: Generalizable Object Placement Learning via Synthetic Augmentation of Human Arrangement
Yao Zhong, Hanzhi Chen, Simon Schaefer et al. (+2 more)
Robots are expected to serve as intelligent assistants, helping humans with everyday household organization. A central challenge in this setting is the task of object placement, which requires
reasoning about both semantic preferences (e.g., common-sense object relations) and
geometric feasibility (e.g., collision avoidance). We present GOPLA, a hierarchical framework that learns generalizable object placement from augmented human demonstrations. A multi-modal large
language model translates human instructions and visual inputs into structured plans that specify pairwise object relationships. These plans are then converted into 3D affordance maps with
geometric common sense by a spatial mapper, while a
diffusion-based planner generates placement poses guided by test-time costs, considering multi-plan distributions and collision avoidance. To overcome data scarcity, we introduce a scalable pipeline that expands human placement demonstrations into diverse synthetic training data. Extensive experiments show that our approach improves placement success rates by 30.04 percentage points over the runner-up, evaluated on positioning accuracy and physical plausibility, demonstrating strong generalization across a wide range of real-world robotic placement scenarios.
Read the full abstract ▾
All authors Yao Zhong, Hanzhi Chen, Simon Schaefer, Anran Zhang, Stefan Leutenegger