On the Efficacy of 3D Point Cloud Reinforcement Learning
Recent studies on visual reinforcement learning (visual RL) have explored the use of 3D visual representations. However, none of these work has systematically compared the efficacy of 3D representations with 2D representations across different tasks, nor have they analyzed 3D representations from the perspective of agent-object / object-object relationship reasoning. In this work, we seek answers to the question of when and how do 3D neural networks that learn features in the 3D-native space provide a beneficial inductive bias for visual RL. We specifically focus on 3D point clouds, one of the most common forms of 3D representations. We systematically investigate design choices for 3D point cloud RL, leading to the development of a robust algorithm for various robotic manipulation and control tasks. Furthermore, through comparisons between 2D image vs 3D point cloud RL methods on both minimalist synthetic tasks and complex robotic manipulation tasks, we find that 3D point cloud RL can significantly outperform the 2D counterpart when agent-object / object-object relationship encoding is a key factor.
Code (1)
Tasks
3D Point Cloud Reinforcement LearningInductive BiasObjectreinforcement-learningReinforcement LearningRobot ManipulationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
An Efficient Hypergraph Approach to Robust Point Cloud Resampling
Efficient processing and feature extraction of largescale point clouds are important in related computer vision and cyber-physical systems. This work investigates point cloud resampling based on hypergraph signal process…
Point cloud segmentation using hierarchical tree for architectural models
Recent developments in the 3D scanning technologies have made the generation of highly accurate 3D point clouds relatively easy but the segmentation of these point clouds remains a challenging area. A number of technique…
Point Cloud SegmentationSegmentationHypergraph Spectral Analysis and Processing in 3D Point Cloud
Along with increasingly popular virtual reality applications, the three-dimensional (3D) point cloud has become a fundamental data structure to characterize 3D objects and surroundings. To process 3D point clouds efficie…
DenoisingMahalanobis k-NN: A Statistical Lens for Robust Point-Cloud Registrations
In this paper, we discuss Mahalanobis k-NN: A Statistical Lens designed to address the challenges of feature matching in learning-based point cloud registration when confronted with an arbitrary density of point clouds. …
BenchmarkingPoint Cloud RegistrationRobust Point Cloud Reinforcement Learning via PCA-Based Canonicalization
Reinforcement Learning (RL) from raw visual input has achieved impressive successes in recent years, yet it remains fragile to out-of-distribution variations such as changes in lighting, color, and viewpoint. Point Cloud…
Reinforcement LearningPoint Clouds