Trajectory Tracking and Imitation of Robotic Quadrupeds Using DeepLabCut

Quadrupedal robotics is an ever growing field with a wide range of applications. However, developing controllers for new behaviours can be challenging due to the complex nature of these robots. Imitation learning algorithms can help overcome some of these challenges, with robots learning from biological counterparts through motion capture data. Robots could also potentially use these techniques for copying behaviours from other robots/animals of similar morphology. Acquiring the required motion capture data from animals and remote locations can be difficult due to the bulky expensive equipment required. However, the use of pose estimation toolboxes such as DeepLabCut could negate this issue. This paper covers the methodology and results from initial proof of concept experiments for two key areas. Firstly, testing the feasibility of DeepLabCut in the use of tracking robotic quadrupeds. Secondly, if the data produced can be used to generate trajectories for deployment on a target robot. This will help to establish if the use of pose estimation toolboxes could potentially be useful in future imitation learning experiments.