Summary
Tracking a moving target with a robot means the robot must keep the target in sight and safely avoid obstacles while moving smoothly. The authors introduce LECO, a method that learns to control the robot directly by training on offline data from optimization plans. This approach lets the robot predict control actions that balance movement smoothness and safety by learning from past best plans rather than solving complex math again and again. LECO also uses a safety check during operation to avoid collisions, switching to traditional control if needed. Tests in simulations and real robot scenarios show LECO can track moving targets more smoothly and successfully than other methods.
What this means in practice
- •For robotics engineers: Develop smoother and more reliable target tracking controllers for robots navigating cluttered and dynamic environments using learned direct control policies.
- •For autonomous vehicle developers: Enhance vehicle navigation systems to smoothly follow moving objects or people by integrating learned control policies that balance obstacle avoidance with tracking.
Authors
Bing Sun, Yue Lin, Canhui Wen, Xin Chen, Yang Liu, Dong Wang, Huchuan Lu
Abstract
Dynamic target tracking requires a mobile robot to maintain target visibility while navigating obstacles with smooth, feasible controls. Online trajectory optimization explicitly encodes these objectives but requires repeated numerical solving, whereas waypoint-based neural policies separate geometric prediction from control execution. We introduce LECO, a framework that transfers tracking optimization into offline learning of a direct-control policy. LECO predicts control sequences and maps them to trajectories through a differentiable kinematic model, allowing trajectory-level objectives to directly guide control learning. A decaying expert-guidance curriculum initializes effective tracking behavior and progressively shifts learning toward these task objectives. At deployment, a predictive safety lock checks short-horizon obstacle clearance and invokes a classical planning and control fallback when the predicted motion is unsafe or the target prediction is invalid. Across three simulated obstacle densities, LECO reduces root-mean-square linear jerk by 14.1--31.2\% relative to the best competing method for this metric and achieves the highest tracking success rate, with per-cycle computation times of 4.25--5.63\,ms. Experiments on two robot platforms further demonstrate tracking through indoor narrow passages and outdoor forest environments. These results demonstrate that learning direct control from optimization enables smooth and robust dynamic target tracking.