Learning-based Nonlinear Model Predictive Control to Improve Vision-based Mobile Robot Path Tracking

PDF

Authors
  1. Ostafew, C.J.
  2. Collier, J.
  3. Schoellig, A.P.
  4. Barfoot, T.D.
Corporate Authors
Defence Research and Development Canada, Suffield Research Centre, Ralston AB (CAN);Toronto Univ, Downsview ONT (CAN) Inst for Aerospace Studies
Abstract
This paper presents a Learning-based Nonlinear Model Predictive Control (LB-NMPC) algorithm to achieve high-performance path tracking in challenging off-road terrain through learning. The LB-NMPC algorithm uses a simple a priori vehicle model and a learned disturbance model. Disturbances are modelled as a Gaussian Process (GP) as a function of system state, input, and other relevant variables. The GP is updated based on experience collected during previous trials. Localization for the controller is provided by an on-board, vision-based mapping and navigation system enabling operation in large-scale, GPS-denied environments. The paper presents experimental results including over 3 km of travel by three significantly different robot platforms with masses ranging from 50 kg to 600 kg and at speeds ranging from 0.35 m/s to 1.2 m/s.1 Planned speeds are generated by a novel experience-based speed scheduler that balances overall travel time, path-tracking errors, and localization reliability. The results show that the controller can start from a generic a priori vehicle model and subsequently learn to reduce vehicle- and trajectory-specific path-tracking errors based on experience.
Keywords
model predictive control;computer vision;path following;visual navigation
Report Number
DRDC-RDDC-2015-P024 — External Literature
Date of publication
01 Jun 2015
Number of Pages
34
DSTKIM No
CA040468
CANDIS No
801579
Format(s):
Electronic Document(PDF)

Permanent link

Document 1 of 1

Date modified: