RobotDiffuse Dataset
收藏资源简介:
RobotDiffuse数据集由北京航空航天大学的研究团队创建,旨在支持冗余机械臂的运动规划研究。该数据集包含3500万条机器人姿态数据和14万条避障场景数据,数据来源于复杂的仿真环境。数据集的创建过程通过Pybullet仿真器生成,结合了物理约束和点云编码技术,确保了数据的多样性和复杂性。该数据集主要用于机器人运动规划领域,特别是冗余机械臂在动态环境中的路径生成和避障任务,旨在提高运动规划的效率和稳定性。
The RobotDiffuse dataset was developed by a research team from Beihang University to support research on motion planning for redundant robotic arms. This dataset contains 35 million robotic pose records and 140,000 obstacle avoidance scenario records sourced from complex simulated environments. The dataset was generated using the Pybullet simulator, integrating physical constraints and point cloud encoding techniques to ensure the diversity and complexity of the data. This dataset is primarily utilized in the field of robotic motion planning, particularly for path generation and obstacle avoidance tasks of redundant robotic arms in dynamic environments, with the goal of improving the efficiency and stability of motion planning.

- 1RobotDiffuse: Motion Planning for Redundant Manipulator based on Diffusion Model北京航空航天大学 · 2024年



