Learning to Predict an Ensemble of Planners


There is growing interest in applying machine learning to motion planning. Potential applications are pre- dicting an initial seed for trajectory optimization, predicting an effective heuristic for search based planning, and even predicting a planning algorithm for adaptive motion planning systems. In these situations, providing only a single prediction is unsatisfactory. It leads to many scenarios where the prediction suffers a high loss. In this paper, we advocate list prediction. Each predictor in a list focusses on different regions in the space of environments. This overcomes the shortcoming of a single predictor, and improves overall performance. A framework for list prediction, CONSEQOPT, already exists. Our contribution is an extensive domain-specific treatment. We provide a rigorous and clear exposition of the procedure for training a list of predictors. We provide experimental results on a spectrum of motion planning applications. Each application contributes to understanding the behavior of list prediction. We observe that the benefit of list prediction over a single prediction is significant, irrespective of the application.

Related Publications

List Prediction Applied To Motion Planning
Abhijeet Tallavajhula, Sanjiban Choudhury, Sebastian Scherer, Alonzo Kelly
2016 IEEE International Conference on Robotics and Automation (ICRA) May, 2016
List prediction for motion planning: Case studies
Abhijeet Tallavajhula and Sanjiban Choudhury
CMU-RI-TR-15-25 October, 2015