Trajectory Planning of Robotic Manipulator in Dynamic Environment Exploiting DRL

TL;DR

This paper presents a reinforcement learning approach using DDPG for trajectory planning of a 7-DOF robotic arm in dynamic environments, enabling obstacle avoidance and object manipulation within time constraints.

Contribution

It introduces a novel application of DDPG for real-time trajectory planning in dynamic, unknown environments with moving obstacles.

Findings

DDPG effectively enables obstacle avoidance in dynamic settings.

Sparse rewards perform comparably to dense rewards in training efficiency.

The method achieves successful pick-and-place tasks within fixed time constraints.

Abstract

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.