Constant Time-Delay Leader Following with Neural Networks and Invariant Extended Kalman Filters for Arbitrary Trajectories
For autonomous vehicle convoy systems, this work addresses the challenge of leader tracking under communication constraints and long delays, but the improvements over baselines are not quantified with concrete numbers.
This paper presents a method for constant time-delay leader following in vehicle convoys without inter-vehicle communication or global positioning, integrating a Seq2Seq neural network with an IEKF to predict leader trajectories on SE(2). The approach handles arbitrary nonlinear trajectories and reduces expert domain knowledge, validated through simulations and real robot experiments.
This paper proposes a constant time-delay trajectory tracking method for vehicle convoys operating without inter-vehicle communication, a common coordinate system, or global positioning. The method integrates a probabilistic sequence-to-sequence (Seq2Seq) neural network with an invariant extended Kalman filter (IEKF) to warm-start the prediction process, allowing accurate estimation of a leader vehicle's relative trajectory on the SE(2) manifold. A geometric model predictive controller is further incorporated to fully exploit the manifold-based trajectory predictions for improved control performance. The system can handle arbitrary nonlinear trajectories with varying speeds and motion profiles while reducing the need for expert-based domain knowledge for the design of trajectory following systems, even under long trajectory delays. The effectiveness of the method is validated through comparisons with a pure IEKF baseline, learning-based methods, and the ground-truth trajectory in kinematic simulations, as well as in experiments using real robotic vehicles.