arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.16652cs.ROcs.SYeess.SY
收藏

动态环境下利用DRL的机械臂轨迹规划

Trajectory Planning of Robotic Manipulator in Dynamic Environment Exploiting DRL

Lahore University of Management and Sciences(拉合尔管理科学大学);Speridian Technologies(斯佩里迪安技术公司)

Osama Ahmad, Zawar Hussain, Hammad Naeem

AI总结:

本研究针对未知动态环境下机械臂的轨迹规划问题,应用DDPG算法控制7自由度机械臂避开随机移动障碍物完成拾放任务,并对比了密集与稀疏奖励下的模型效率。

摘要:

本研究涉及在机械臂轨迹规划中实现强化学习算法。我们使用7自由度机械臂,在未知环境中将随机放置的方块拾取并放置到随机目标点。障碍物随机移动,为拾取物体制造了障碍。机器人的目标是避开障碍物,并在固定时间戳的约束下拾取方块。在本文中,我们应用了深度确定性策略梯度(DDPG)算法,并比较了模型在密集奖励和稀疏奖励下的效率。

英文摘要:

This study is about the implementation of a reinforcement learning algorithm in the trajectory planning of manipulators. We have a 7-DOF robotic arm to pick and place the randomly placed block at a random target point in an unknown environment. The obstacle is randomly moving which creates a hurdle in picking the object. The objective of the robot is to avoid the obstacle and pick the block with constraints to a fixed timestamp. In this literature, we have applied a deep deterministic policy gradient (DDPG) algorithm and compared the model's efficiency with dense and sparse rewards.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑