paper-with-me

홈 › Papers

Neural MP: A Generalist Neural Motion Planner

2024-09-09 · Murtaza Dalal, Jiahui Yang, Russell Mendonca, Youssef Khaky, Ruslan Salakhutdinov, Deepak Pathak

The current paradigm for motion planning generates solutions from scratch for every new problem, which consumes significant amounts of time and computational resources. For complex, cluttered scenes, motion planning approaches can often take minutes to produce a solution, while humans are able to accurately and safely reach any goal in seconds by leveraging their prior experience. We seek to do the same by applying data-driven learning at scale to the problem of motion planning. Our approach builds a large number of complex scenes in simulation, collects expert data from a motion planner, then distills it into a reactive generalist policy. We then combine this with lightweight optimization to obtain a safe path for real world deployment. We perform a thorough evaluation of our method on 64 motion planning tasks across four diverse environments with randomized poses, scenes and obstacles, in the real world, demonstrating an improvement of 23%, 17% and 79% motion planning success rate over state of the art sampling, optimization and learning based planning methods. Video results available at mihdalal.github.io/neuralmotionplanner

📄 PDF Abstract BibTeX arXiv:2409.05864

Code (0)

등록된 구현이 없습니다.

Tasks

Motion Planning

Similar Papers 제목 키워드 기반

Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities

2026-03-25 · Davood Soleymanzadeh, Ivan Lopez-Sanchez, Hao Su, Yunzhu Li 외 arxiv

State-of-the-art generalist manipulation policies have enabled the deployment of robotic manipulators in unstructured human environments. However, these frameworks struggle in cluttered environments primarily because the…

Motion Planning

PerFACT: Motion Policy with LLM-Powered Dataset Synthesis and Fusion Action-Chunking Transformers

2025-12-03 · Davood Soleymanzadeh, Xiao Liang, Minghui Zheng arxiv

Deep learning methods have significantly enhanced motion planning for robotic manipulators by leveraging prior experiences within planning datasets. However, state-of-the-art neural motion planners are primarily trained …

Motion Planning

GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots

2025-09-22 · Vassil Atanassov, Wanming Yu, Siddhant Gangapurwala, James Wilson 외 arxiv

Most modern approaches to quadruped locomotion focus on using Deep Reinforcement Learning (DRL) to learn policies from scratch, in an end-to-end manner. Such methods often fail to scale, as every new problem or applicati…

Reinforcement Learning

H-GAP: Humanoid Control with a Generalist Planner

2023-12-05 · Zhengyao Jiang, Yingchen Xu, Nolan Wagener, Yicheng Luo 외

Humanoid control is an important research challenge offering avenues for integration into human-centric infrastructures and enabling physics-driven humanoid animations. The daunting challenges in this field stem from the…

Humanoid ControlModel Predictive ControlOffline RL

Extreme-RGMT: Continual Learning of Highly Dynamic Skills for Robust Generalist Humanoid Control

2026-07-22 · Yubiao Ma, Han Yu, Kai Guo, Changtai Lv 외 arxiv

Humans can progressively acquire highly dynamic motor skills while preserving reliable everyday motor abilities. In contrast, existing humanoid controllers face a trade-off between generalist and specialist capabilities:…

Continual Learning