Robot Manipulation and Learning

Latest papers

• Real-World Reinforcement Learning of Active Perception Behaviors

  Edward S. Hu, Jie Wang, Xingfang Yuan, Fiona Luo, Muyao Li, Gaspard Lambrechts, Oleh Rybkin, Dinesh Jayaraman · 2 December 2025

  A robot's instantaneous sensory observations do not always reveal task-relevant state information. Under such partial observability, optimal behavior typically involves explicitly acting to gain the missing information. Today's standard robot learning techniques struggle to produce such active perce…

• GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation

  Yunfei Li, Xiao Ma, Jiafeng Xu, Yu Cui, Zhongren Cui, Zhigang Han, Liqun Huang, Tao Kong, Yuxiao Liu, Hao Niu, Wanli Peng, Jingchao Qiao, Zeyu Ren, Haixin Shi, Zhi Su, Jiawen Tian, Yuyang Xiao, Shenyu Zhang, Liwei Zheng, Hang Li, Yonghui Wu · 2 December 2025

  We present GR-RL, a robotic learning framework that turns a generalist vision-language-action (VLA) policy into a highly capable specialist for long-horizon dexterous manipulation. Assuming the optimality of human demonstrations is core to existing VLA policies. However, we claim that in highly dext…

• RealAppliance: Let High-fidelity Appliance Assets Controllable and Workable as Aligned Real Manuals

  Yuzheng Gao, Yuxing Long, Lei Kang, Yuchong Guo, Ziyan Yu, Shangqing Mao, Jiyao Zhang, Ruihai Wu, Dongjiang Li, Hui Shen, Hao Dong · 2 December 2025

  Existing appliance assets suffer from poor rendering, incomplete mechanisms, and misalignment with manuals, leading to simulation-reality gaps that hinder appliance manipulation development. In this work, we introduce the RealAppliance dataset, comprising 100 high-fidelity appliances with complete p…

• RoboArena: Distributed Real-World Evaluation of Generalist Robot Policies

  Pranav Atreya, Karl Pertsch, Tony Lee, Moo Jin Kim, Arhan Jain, Artur Kuramshin, Clemens Eppner, Cyrus Neary, Edward Hu, Fabio Ramos, Jonathan Tremblay, Kanav Arora, Kirsty Ellis, Luca Macesanu, Marcel Torne Villasevil, Matthew Leonard, Meedeum Cho, Ozgur Aslan, Shivin Dass, Jie Wang, William Reger, Xingfang Yuan, Xuning Yang, Abhishek Gupta, Dinesh Jayaraman, Glen Berseth, Kostas Daniilidis, Roberto Martin-Martin, Youngwoon Lee, Percy Liang, Chelsea Finn, Sergey Levine · 2 December 2025

  Comprehensive, unbiased, and comparable evaluation of modern generalist policies is uniquely challenging: existing approaches for robot benchmarking typically rely on heavy standardization, either by specifying fixed evaluation tasks and environments, or by hosting centralized ''robot challenges'', …

• Modality-Augmented Fine-Tuning of Foundation Robot Policies for Cross-Embodiment Manipulation on GR1 and G1

  Junsung Park, Hogun Kee, Songhwai Oh · 2 December 2025

  This paper presents a modality-augmented fine-tuning framework designed to adapt foundation robot policies to diverse humanoid embodiments. We validate our approach across two distinct settings: (i) the GR1 embodiment, utilizing public datasets where we introduce post-processed modalities, including…

• Constant-Time Motion Planning with Manipulation Behaviors

  Nayesha Gandotra, Itamar Mishani, Maxim Likhachev · 2 December 2025

  Recent progress in contact-rich robotic manipulation has been striking, yet most deployed systems remain confined to simple, scripted routines. One of the key barriers is the lack of motion planning algorithms that can provide verifiable guarantees for safety, efficiency and reliability. To address …

• EfficientFlow: Efficient Equivariant Flow Policy Learning for Embodied AI

  Jianlei Chang, Ruofeng Mei, Wei Ke, Xiangyu Xu · 2 December 2025

  Generative modeling has recently shown remarkable promise for visuomotor policy learning, enabling flexible and expressive control across diverse embodied AI tasks. However, existing generative policies often struggle with data inefficiency, requiring large-scale demonstrations, and sampling ineffic…

• Real-World Robot Control by Deep Active Inference With a Temporally Hierarchical World Model

  Kentaro Fujii, Shingo Murata · 2 December 2025

  Robots in uncertain real-world environments must perform both goal-directed and exploratory actions. However, most deep learning-based control methods neglect exploration and struggle under uncertainty. To address this, we adopt deep active inference, a framework that accounts for human goal-directe…

• Obstruction reasoning for robotic grasping

  Runyu Jiao, Matteo Bortolon, Francesco Giuliari, Alice Fasoli, Sergio Povoli, Guofeng Mei, Yiming Wang, Fabio Poiesi · 1 December 2025

  Successful robotic grasping in cluttered environments not only requires a model to visually ground a target object but also to reason about obstructions that must be cleared beforehand. While current vision-language embodied reasoning models show emergent spatial understanding, they remain limited i…

• CAPE: Context-Aware Diffusion Policy Via Proximal Mode Expansion for Collision Avoidance

  Rui Heng Yang, Xuan Zhao, Leo Maxime Brunswic, Montgomery Alban, Mateo Clemente, Tongtong Cao, Jun Jin, Amir Rasouli · 1 December 2025

  In robotics, diffusion models can capture multi-modal trajectories from demonstrations, making them a transformative approach in imitation learning. However, achieving optimal performance following this regiment requires a large-scale dataset, which is costly to obtain, especially for challenging ta…

• Improving Robotic Manipulation Robustness via NICE Scene Surgery

  Sajjad Pakdamansavoji, Mozhgan Pourkeshavarz, Adam Sigal, Zhiyuan Li, Rui Heng Yang, Amir Rasouli · 1 December 2025

  Learning robust visuomotor policies for robotic manipulation remains a challenge in real-world settings, where visual distractors can significantly degrade performance and safety. In this work, we propose an effective and scalable framework, Naturalistic Inpainting for Context Enhancement (NICE). Ou…

• VacuumVLA: Boosting VLA Capabilities via a Unified Suction and Gripping Tool for Complex Robotic Manipulation

  Hui Zhou, Siyuan Huang, Minxing Li, Hao Zhang, Lue Fan, Shaoshuai Shi · 27 November 2025

  Vision Language Action models have significantly advanced general purpose robotic manipulation by harnessing large scale pretrained vision and language representations. Among existing approaches, a majority of current VLA systems employ parallel two finger grippers as their default end effectors. Ho…

• Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy

  Inkook Chun, Seungjae Lee, Michael S. Albergo, Saining Xie, Eric Vanden-Eijnden · 27 November 2025

  Diffusion- and flow-based policies deliver state-of-the-art performance on long-horizon robotic manipulation and imitation learning tasks. However, these controllers employ a fixed inference budget at every control step, regardless of task complexity, leading to computational inefficiency for simple…

• "Are We Done Yet?": A Vision-Based Judge for Autonomous Task Completion of Computer Use Agents

  Marta Sumyk, Oleksandr Kosovan · 26 November 2025

  Computer Use Agents (CUAs) are designed to autonomously operate digital interfaces, yet they often fail to reliably determine whether a given task has been completed. We present an autonomous evaluation and feedback framework that uses vision-language models to assess task completion directly from s…

• Unreal Robotics Lab: A High-Fidelity Robotics Simulator with Advanced Physics and Rendering

  Jonathan Embley-Riches, Jianwei Liu, Simon Julier, Dimitrios Kanoulas · 25 November 2025

  High-fidelity simulation is essential for robotics research, enabling safe and efficient testing of perception, control, and navigation algorithms. However, achieving both photorealistic rendering and accurate physics modeling remains a challenge. This paper presents a novel simulation framework, th…

• Reinforcement Learning for Self-Healing Material Systems

  Maitreyi Chatterjee, Devansh Agarwal, Biplab Chatterjee · 25 November 2025

  The transition to autonomous material systems necessitates adaptive control methodologies to maximize structural longevity. This study frames the self-healing process as a Reinforcement Learning (RL) problem within a Markov Decision Process (MDP), enabling agents to autonomously derive optimal polic…

• Observer Actor: Active Vision Imitation Learning with Sparse View Gaussian Splatting

  Yilong Wang, Cheng Qian, Ruomeng Fan, Edward Johns · 25 November 2025

  We propose Observer Actor (ObAct), a novel framework for active vision imitation learning in which the observer moves to optimal visual observations for the actor. We study ObAct on a dual-arm robotic system equipped with wrist-mounted cameras. At test time, ObAct dynamically assigns observer and ac…

• A Coordinated Dual-Arm Framework for Delicate Snap-Fit Assemblies

  Shreyas Kumar, Barat S, Debojit Das, Yug Desai, Siddhi Jain, Rajesh Kumar, Harish J. Palanthandalam-Madapusi · 25 November 2025

  Delicate snap-fit assemblies, such as inserting a lens into an eye-wear frame or during electronics assembly, demand timely engagement detection and rapid force attenuation to prevent overshoot-induced component damage or assembly failure. We address these challenges with two key contributions. Firs…

• RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis

  Linfeng Dong, Yuchen Yang, Hao Wu, Wei Wang, Yuenan HouZhihang Zhong, Xiao Sun · 24 November 2025

  We introduce RacketVision, a novel dataset and benchmark for advancing computer vision in sports analytics, covering table tennis, tennis, and badminton. The dataset is the first to provide large-scale, fine-grained annotations for racket pose alongside traditional ball positions, enabling research …

• Leveraging CVAE for Joint Configuration Estimation of Multifingered Grippers from Point Cloud Data

  Julien Merand, Boris Meden, Mathieu Grossard · 24 November 2025

  This paper presents an efficient approach for determining the joint configuration of a multifingered gripper solely from the point cloud data of its poly-articulated chain, as generated by visual sensors, simulations or even generative neural networks. Well-known inverse kinematics (IK) techniques c…

• Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations

  Irmak Guzey, Haozhi Qi, Julen Urain, Changhao Wang, Jessica Yin, Krishna Bodduluri, Mike Lambeta, Lerrel Pinto, Akshara Rai, Jitendra Malik, Tingfan Wu, Akash Sharma, Homanga Bharadhwaj · 21 November 2025

  Learning multi-fingered robot policies from humans performing daily tasks in natural environments has long been a grand goal in the robotics community. Achieving this would mark significant progress toward generalizable robot manipulation in human environments, as it would reduce the reliance on lab…

• WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusion

  Sajjad Pakdamansavoji, Yintao Ma, Amir Rasouli, Tongtong Cao · 21 November 2025

  Accurate 6D object pose estimation is vital for robotics, augmented reality, and scene understanding. For seen objects, high accuracy is often attainable via per-object fine-tuning but generalizing to unseen objects remains a challenge. To address this problem, past arts assume access to CAD models …

• Box6D : Zero-shot Category-level 6D Pose Estimation of Warehouse Boxes

  Yintao Ma, Sajjad Pakdamansavoji, Amir Rasouli, Tongtong Cao · 21 November 2025

  Accurate and efficient 6D pose estimation of novel objects under clutter and occlusion is critical for robotic manipulation across warehouse automation, bin picking, logistics, and e-commerce fulfillment. There are three main approaches in this domain; Model-based methods assume an exact CAD model a…

• Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning

  Rickmer Krohn, Vignesh Prasad, Gabriele Tiboni, Georgia Chalvatzaki · 19 November 2025

  Effective contact-rich manipulation requires robots to synergistically leverage vision, force, and proprioception. However, Reinforcement Learning agents struggle to learn in such multisensory settings, especially amidst sensory noise and dynamic changes. We propose MultiSensory Dynamic Pretraining …

• From Power to Precision: Learning Fine-grained Dexterity for Multi-fingered Robotic Hands

  Jianglong Ye, Lai Wei, Guangqi Jiang, Changwei Jing, Xueyan Zou, Xiaolong Wang · 18 November 2025

  Human grasps can be roughly categorized into two types: power grasps and precision grasps. Precision grasping enables tool use and is believed to have influenced human evolution. Today's multi-fingered robotic hands are effective in power grasps, but for tasks requiring precision, parallel grippers …