paper-with-me

홈 › Papers

Neural Volumetric Memory for Visual Locomotion Control

2023-04-03 · CVPR 2023 1 · Ruihan Yang, Ge Yang, Xiaolong Wang

Legged robots have the potential to expand the reach of autonomy beyond paved roads. In this work, we consider the difficult problem of locomotion on challenging terrains using a single forward-facing depth camera. Due to the partial observability of the problem, the robot has to rely on past observations to infer the terrain currently beneath it. To solve this problem, we follow the paradigm in computer vision that explicitly models the 3D geometry of the scene and propose Neural Volumetric Memory (NVM), a geometric memory architecture that explicitly accounts for the SE(3) equivariance of the 3D world. NVM aggregates feature volumes from multiple camera views by first bringing them back to the ego-centric frame of the robot. We test the learned visual-locomotion policy on a physical robot and show that our approach, which explicitly introduces geometric priors during training, offers superior performance than more na\"ive methods. We also include ablation studies and show that the representations stored in the neural volumetric memory capture sufficient geometric information to reconstruct the scene. Our project page with videos is https://rchalyang.github.io/NVM .

📄 PDF Abstract BibTeX arXiv:2304.01201

Code (0)

등록된 구현이 없습니다.

Tasks

3D geometry

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Bayesian Relational Memory for Semantic Visual Navigation

2019-09-10 · ICCV 2019 10 · Yi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell 외

We introduce a new memory architecture, Bayesian Relational Memory (BRM), to improve the generalization ability for semantic visual navigation agents in unseen environments, where an agent is given a semantic target to n…

NavigateVisual Navigation

RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion

2025-12-29 · Zhe Li, Cheng Chi, Boan Zhu, Yangyang Wei 외 arxiv

Humans learn locomotion through visual observation, interpreting visual content first before imitating actions. However, state-of-the-art humanoid locomotion systems rely on either curated motion capture trajectories or …

Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient

2026-05-26 · Haoxiang You, Yilang Liu, Davis Zong, Qian Wang 외 arxiv

We present the stochastic decoupled policy gradient (SDPG), a lightweight visual reinforcement learning (RL) method that trains diverse visuomotor control policies end-to-end within a few hours on a single NVIDIA RTX 408…

Reinforcement Learning

Neuromorphic Reinforcement Learning for Quadruped Locomotion Control on Uneven Terrain

2026-05-10 · Zhuangyu Han, Abhronil Sengupta arxiv

Reinforcement learning (RL) has enabled robust quadruped locomotion over complex terrain, but most learned controllers are trained offline with backpropagation in massively parallel simulation and deployed as fixed polic…

Reinforcement Learning

Iteratively Learning Muscle Memory for Legged Robots to Master Adaptive and High Precision Locomotion

2025-07-18 · Jing Cheng, Yasser G. Alqaham, Zhenyu Gan, Amit K. Sanyal arxiv

This paper presents a scalable and adaptive control framework for legged robots that integrates Iterative Learning Control (ILC) with a biologically inspired torque library (TL), analogous to muscle memory. The proposed …