English
Related papers

Related papers: R3D: Revisiting 3D Policy Learning

200 papers

Reinforcement learning (RL) has emerged as a crucial approach for enhancing the capabilities of large language models. However, in Mixture-of-Experts (MoE) models, the routing mechanism often introduces instability, even leading to…

Computation and Language · Computer Science 2025-10-22 Wenhan Ma , Hailin Zhang , Liang Zhao , Yifan Song , Yudong Wang , Zhifang Sui , Fuli Luo

This paper focuses on transferring control policies between robot manipulators with different morphology. While reinforcement learning (RL) methods have shown successful results in robot manipulation tasks, transferring a trained policy…

Robotics · Computer Science 2024-06-05 Tianyu Wang , Dwait Bhatt , Xiaolong Wang , Nikolay Atanasov

Legged locomotion is a complex control problem that requires both accuracy and robustness to cope with real-world challenges. Legged systems have traditionally been controlled using trajectory optimization with inverse dynamics. Such…

Robotics · Computer Science 2024-01-23 Fabian Jenelten , Junzhe He , Farbod Farshidian , Marco Hutter

3D Object Detectors (3D-OD) are crucial for understanding the environment in many robotic tasks, especially autonomous driving. Including 3D information via Lidar sensors improves accuracy greatly. However, such detectors perform poorly on…

Computer Vision and Pattern Recognition · Computer Science 2024-02-28 George Eskandar , Chongzhe Zhang , Abhishek Kaushik , Karim Guirguis , Mohamed Sayed , Bin Yang

Vision-based robotics often separates the control loop into one module for perception and a separate module for control. It is possible to train the whole system end-to-end (e.g. with deep RL), but doing it "from scratch" comes with a high…

Robotics · Computer Science 2020-11-16 Bryan Chen , Alexander Sax , Gene Lewis , Iro Armeni , Silvio Savarese , Amir Zamir , Jitendra Malik , Lerrel Pinto

Random delays weaken the temporal correspondence between actions and subsequent state feedback, making it difficult for agents to identify the true propagation process of action effects. In cross-task scenarios, changes in task objectives…

Machine Learning · Computer Science 2026-05-13 Chenran Zhao , Dianxi Shi , Yaowen Zhang , Chunping Qiu , Shaowu Yang

Training deep neural network policies end-to-end for real-world applications so far requires big demonstration datasets in the real world or big sets consisting of a large variety of realistic and closely related 3D CAD models. These real…

Robotics · Computer Science 2018-04-13 Klaas Kelchtermans , Tinne Tuytelaars

We introduce GROOT, an imitation learning method for learning robust policies with object-centric and 3D priors. GROOT builds policies that generalize beyond their initial training conditions for vision-based manipulation. It constructs…

Robotics · Computer Science 2023-10-24 Yifeng Zhu , Zhenyu Jiang , Peter Stone , Yuke Zhu

Vision-based imitation learning has enabled impressive robotic manipulation skills, but its reliance on object appearance while ignoring the underlying 3D scene structure leads to low training efficiency and poor generalization. To address…

Robotics · Computer Science 2026-03-03 Wenlong Xia , Jinhao Zhang , Ce Zhang , Yaojia Wang , Huizhe Li , Youmin Gong , Jie Mei

Visual representations play a crucial role in developing generalist robotic policies. Previous vision encoders, typically pre-trained with single-image reconstruction or two-image contrastive learning, tend to capture static information,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Yucheng Hu , Yanjiang Guo , Pengchao Wang , Xiaoyu Chen , Yen-Jen Wang , Jianke Zhang , Koushil Sreenath , Chaochao Lu , Jianyu Chen

This work considers the problem of transfer learning in the context of reinforcement learning. Specifically, we consider training a policy in a reduced order system and deploying it in the full state system. The motivation for this training…

Machine Learning · Computer Science 2024-10-10 Shima Rabiei , Sandipan Mishra , Santiago Paternain

In this work we propose an approach to learn a robust policy for solving the pivoting task. Recently, several model-free continuous control algorithms were shown to learn successful policies without prior knowledge of the dynamics of the…

Robotics · Computer Science 2017-03-03 Rika Antonova , Silvia Cruciani , Christian Smith , Danica Kragic

Whereas reinforcement learning has been applied with success to a range of robotic control problems in complex, uncertain environments, reliance on extensive data - typically sourced from simulation environments - limits real-world…

Robotics · Computer Science 2026-01-29 Jamie Hathaway , Alireza Rastegarpanah , Rustam Stolkin

Recent research has highlighted the powerful capabilities of imitation learning in robotics. Leveraging generative models, particularly diffusion models, these approaches offer notable advantages such as strong multi-task generalization,…

Robotics · Computer Science 2025-09-15 Xinyao Qin , Xiaoteng Ma , Yang Qi , Qihan Liu , Chuanyi Xue , Ning Gui , Qinyu Dong , Jun Yang , Bin Liang

Reusing large datasets is crucial to scale vision-based robotic manipulators to everyday scenarios due to the high cost of collecting robotic datasets. However, robotic platforms possess varying control schemes, camera viewpoints, kinematic…

Robotics · Computer Science 2023-07-10 Jonathan Yang , Dorsa Sadigh , Chelsea Finn

Cross-embodiment learning seeks to build generalist robots that operate across diverse morphologies, but differences in action spaces and kinematics hinder data sharing and policy transfer. This raises a central question: Is there any…

Robotics · Computer Science 2025-11-11 Zihao He , Bo Ai , Tongzhou Mu , Yulin Liu , Weikang Wan , Jiawei Fu , Yilun Du , Henrik I. Christensen , Hao Su

Tool use is essential for enabling robots to perform complex real-world tasks, but learning such skills requires extensive datasets. While teleoperation is widely used, it is slow, delay-sensitive, and poorly suited for dynamic tasks. In…

Robotics · Computer Science 2025-09-16 Haonan Chen , Cheng Zhu , Shuijing Liu , Yunzhu Li , Katherine Driggs-Campbell

Modern image encoders achieve high generalization by decoupling semantic meaning from resolution, an ability yet to be fully realized in the 3D domain. We investigate the failure of 3D point cloud encoders to achieve similar generalization…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Chun-Peng Chang , Shaoxiang Wang , Alain Pagani , Dariu Gavrila , Holger Caesar

Imitation Learning presents a promising approach for learning generalizable and complex robotic skills. The recently proposed Diffusion Policy generates robot action sequences through a conditional denoising diffusion process, achieving…

Machine Learning · Computer Science 2024-12-03 Xiu Yuan

The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages. This promotes the potential of utilizing models…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Runpei Dong , Zekun Qi , Linfeng Zhang , Junbo Zhang , Jianjian Sun , Zheng Ge , Li Yi , Kaisheng Ma