10 papers
DualWAM: Dual-System World Action Models for Asynchronous Global Planning and Local Refinement
Yixin Zheng, Jiangran Lyu, Yuntian Deng +6
World Action Models (WAMs) jointly generate robot actions and predict future world states, transferring priors from video pretraining to robot control. However, future visual predi…
WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time
Yusen Feng, Bingchen Han, Jiangran Lyu +13
Steering robot foundation models (RFMs) toward new task variants or user-preferred behaviors remains challenging, often requiring additional robot demonstrations, task-specific fin…
HDFlow: Hierarchical Diffusion-Flow Planning for Long-horizon Tasks
Nandiraju Gireesh, Yuanliang Ju, Chaoyi Xu +3
Recent advances in generative models have shown promise in generating behavior plans for long-horizon, sparse reward tasks. While these approaches have achieved promising results,…
DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo
Hanwen Wang, Weizhi Zhao, Xiangyu Wang +11
Achieving human-level manipulation requires dexterous robotic hands capable of complex object interactions. Advancing such capabilities further demands standardized benchmarks for…
Distributed Zeroth-Order Policy Gradient for Networked Multi-agent Reinforcement Learning from Human Feedback
Pengcheng Dai, He Wang, Dongming Wang +2
We study a networked multi-agent reinforcement learning (NMARL) problem with human feedback in an infinite-horizon setting, where agents interact over an underlying network with lo…
DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation
Jiangran Lyu, Ziming Li, Xuesong Shi +3
Nonprehensile manipulation is crucial for handling objects that are too thin, large, or otherwise ungraspable in unstructured environments. While conventional planning-based approa…
Watch Less, Feel More: Sim-to-Real RL for Generalizable Articulated Object Manipulation via Motion Adaptation and Impedance Control
Tan-Dzung Do, Nandiraju Gireesh, Jilong Wang +1
Articulated object manipulation poses a unique challenge compared to rigid object manipulation as the object itself represents a dynamic environment. In this work, we present a nov…
FetchBot: Learning Generalizable Object Fetching in Cluttered Scenes via Zero-Shot Sim2Real
Weiheng Liu, Yuxuan Wan, Jilong Wang +7
Generalizable object fetching in cluttered scenes remains a fundamental and application-critical challenge in embodied AI. Closely packed objects cause inevitable occlusions, makin…
QuadWBG: Generalizable Quadrupedal Whole-Body Grasping
Jilong Wang, Javokhirbek Rajabov, Chaoyi Xu +2
Legged robots with advanced manipulation capabilities have the potential to significantly improve household duties and urban maintenance. Despite considerable progress in developin…
NAS: N-step computation of All Solutions to the footstep planning problem
Jiayi Wang, Saeid Samadi, Hefan Wang +4
How many ways are there to climb a staircase in a given number of steps? Infinitely many, if we focus on the continuous aspect of the problem. A finite, possibly large number if we…