Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground

<div>Possible detection results. The red circle represents the robot, the red line represents the actual path result, the blue line represents the global path plan, the yellow line represents the local path plan, and the purple rectangle represents the obstacle. (a) Detected incomplete path. (b) Over-detected paths.</div>

Journal of Robotics

fig2

Figure 2

Figure 2: Research on Dynamic Path Planning of Wheeled Robot Based on Deep Reinforcement Learning on the Slope Ground 