Robot Motion Prediction

Latest papers

9 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Proprioceptive Sketches as Long-Horizon Intent for Generative Action Policies
Oct 2, 2026Fangyuan Wang, Songhao Huang, Haoxiang Sun +5Robot Policy Learning Long-Horizon Robotic Manipulation
Hong Kong Polytechnic University · National University of Singapore · Mohamed bin Zayed University of Artificial Intelligence +1
Steering Through Contact: A Finite-Support Motion Model for Single-Track Center-Articulated Robots
Sep 20, 2026Mohamed Dhia Ounally, Nicolas Samson, Mathis Turgeon-Roy +3Robot Motion Prediction Robotics
Norlab, Universit´e Laval, Qu´ebec, QC, Canada · TSCF, INRAE, Clermont-Ferrand, France
MoWAM: Explicit Future Motion Prediction for Efficient World Action Models
Sep 17, 2026Jiayu Wang, Bin Zhu, Yue Yu +1World Models for Robotics World Model-Based Planning
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China · Singapore Management University, Singapore · Institute of Trustworthy Embodied AI, Fudan University, Shanghai, China
Robot Trajectron V3: A Probabilistic Shared Control Framework for SE(3) Manipulation
Jul 10, 2026Pinhao Song, Zhongxi Li, Ze Fu +2Robotic Control Robotic Grasping
KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics, B-3000 Leuven, Belgium. · KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images, B-3000 Leuven, Belgium.
ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation
May 28, 2026Zeyuan He, Bowen Yang, Zhirui Fang +9Language-Conditioned Robot Manipulation Visuomotor Policy Learning
Torr Vision Group, University of Oxford · The Chinese University of Hong Kong, Shenzhen · Shanghai Jiao Tong University +3
Spatially Prompted Visual Trajectory Prediction for Egocentric Manipulation
May 19, 2026Yifan Li, Xinyu Zhou, Yunhao Ge +2Robot Motion Prediction Robotic Manipulation
Michigan State University · NVIDIA Research
WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems
Mar 15, 2026Yuchen Wang, Jiangtao Kong, Sizhe Wei +6Robot Motion Prediction World Models for Robotics
William & Mary · Georgia Institute of Technology · Carnegie Mellon University +2
AutoTraces: Autoregressive Trajectory Forecasting via Multimodal Large Language Models
Mar 9, 2026Teng Wang, Yanting Lu, Ruize WangRobot Motion Prediction Trajectory Prediction
ISS Policy : Scalable Diffusion Policy with Implicit Scene Supervision
Dec 17, 2025Wenlong Xia, Jinhao Zhang, Ce Zhang +6Robot Skill Learning Visuomotor Policy Learning
[cs.RO]

Oct 2, 2026J/K move · Enter open · S save

Proprioceptive Sketches as Long-Horizon Intent for Generative Action Policies

Fangyuan Wang, Songhao Huang, Haoxiang Sun, Shipeng Lyu+4

Hong Kong Polytechnic University · National University of Singapore · Mohamed bin Zayed University of Artificial Intelligence+1

Robot Policy Learning Long-Horizon Robotic Manipulation Robot Motion Prediction Diffusion Models for Motion Generation Visuomotor Policy Learning Trajectory Representation Learning

Open paper AskPDF arXiv

Generative robot policies predict short action chunks but lack explicit long-horizon intent. Recent methods expose longer-horizon structure through language plans, subgoal images, or video forecasts, which are costly to generate and still need to be translated into robot motion. Predicting future robot motions avoids this translation, but a dense, time-indexed trajectory requires numerous parameters to cover the full remaining task, and over a short horizon it largely repeats the action chunk and adds little guidance for action generation. We propose Proprioceptive Action Models (PAM), which jointly generate a compact, timing-free sketch of the robot's remaining joint-space path and a dense executable action chunk within a single transformer denoiser. The sketch parameterizes the path by arc length rather than time, capturing geometric intent invariant to execution timing. Block-causal attention and a staggered denoising schedule maintain directed sketch-to-action dependence, ensuring the action tokens condition on a progressively cleaner sketch throughout sampling. In simulation, PAM improves over its action-only counterparts on Push-T and LIBERO-Long; on four real-world bimanual tasks, it raises success from 47.5% to 75.0%. Project page: https://nicehiro.github.io/pam_dp/