Abstract:Seamlessly integrating rules in Learning-from-Demonstrations (LfD) policies is a critical requirement to enable the real-world deployment of AI agents. Recently Signal Temporal Logic (STL) has been shown to be an effective language for encoding rules as spatio-temporal constraints. This work uses Monte Carlo Tree Search (MCTS) as a means of integrating STL specification into a vanilla LfD policy to improve constraint satisfaction. We propose augmenting the MCTS heuristic with STL robustness values to bias the tree search towards branches with higher constraint satisfaction. While the domain-independent method can be applied to integrate STL rules online into any pre-trained LfD algorithm, we choose goal-conditioned Generative Adversarial Imitation Learning as the offline LfD policy. We apply the proposed method to the domain of planning trajectories for General Aviation aircraft around a non-towered airfield. Results using the simulator trained on real-world data showcase 60% improved performance over baseline LfD methods that do not use STL heuristics.
Abstract:This paper presents a collaborative target tracking application with multiple agents and a formulation of an agent-formation problem with desired inter-agent distances and specified bounds. We propose a barrier Lyapunov function-based distributed control law to preserve the formation for target-tracking and assess its stability using a kinematic model. Numerical results with this model are presented to demonstrate the advantages of the proposed control over a quadratic Lyapunov function-based control. A concluding evaluation using experimental ROS simulations is presented to illustrate the applicability of the proposed control approach to a multi-rotor system and a target executing straight line and circular motion.