Collision-Free Model Predictive Controller for Robots

Robotic Gizmos

Robots are getting smarter all the time. Many of them are capable of detecting and avoiding collisions. This video from Robotic Systems Lab shows a MPC that discovers collision-free locomotion for robots while taking into account constraints and limitations. As the researches explain, this approach:
enables legged robots to find whole-body motions in the presence of static and dynamic obstacles. We use a dynamically generated euclidean signed distance field for static collision checking. Collision checking for dynamic obstacles is modeled with moving cylinders, increasing the responsiveness to fast-moving agents. Furthermore, we include a Kalman filter motion prediction for moving obstacles into our receding horizon planning, enabling the robot to anticipate possible future collisions.

[HT]
The post Collision-Free Model Predictive Controller for Robots appeared first on Robotic Gizmos.
Source: roboticgizmos

Leave a Reply