This paper investigates the collision-free control problem for multi-agent systems. For such multi-agent systems, it is the typical situation where conventional methods using either the usual centralized model predictive control (MPC), or even the distributed counterpart, would suffer from substantial difficulty in balancing optimality and computational efficiency. Additionally, the non-convex characteristics that invariably arise in such collision-free control and optimization problems render it difficult to effectively derive a reliable solution (and also to thoroughly analyze the associated convergence properties). To overcome these challenging issues, this work establishes a suitably novel parallel computation framework through an innovative mathematical problem formulation; and then with this framework and formulation, a parallel algorithm based on alternating direction method of multipliers (ADMM) is presented to solve the sub-problems arising from the resulting parallel structure. Furthermore, an efficient and intuitive initialization procedure is developed to accelerate the optimization process, and the optimum is thus determined with significantly improved computational efficiency. As supported by rigorous proofs, the convergence of the proposed ADMM iterations for this non-convex optimization problem is analyzed and discussed in detail. Finally, a simulation with a group of unmanned aerial vehicles (UAVs) serves as an illustrative example here to demonstrate the effectiveness and efficiency of the proposed approach. Also, the simulation results verify significant improvements in accuracy and computational efficiency compared to other baselines, including primal quadratic mixed integer programming (PQ-MIP), non-convex quadratic mixed integer programming (NC-MIP), and non-convex quadratically constrained quadratic programming (NC-QCQP).

R2 is a novel online any-angle path planner that uses heuristic bug-based or ray casting approaches to find optimal paths in 2D maps with non-convex, polygonal obstacles. R2 is competitive to traditional free-space planners, finding paths quickly if queries have direct line-of-sight. On large sparse maps with few obstacle contours, which are likely to occur in practice, R2 outperforms free-space planners, and can be much faster than state-of-the-art free-space expansion planner Anya. On maps with many contours, Anya performs faster than R2. R2 is built on RayScan, introducing lazy-searches and a source-pledge counter to find successors optimistically on contiguous contours. The novel approach bypasses most successors on jagged contours to reduce expensive line-of-sight checks, therefore requiring no pre-processing to be a competitive online any-angle planner.

In many specific scenarios, accurate and effective system identification is a commonly encountered challenge in the model predictive control (MPC) formulation. As a consequence, the overall system performance could be significantly weakened in outcome when the traditional MPC algorithm is adopted under those circumstances when such accuracy is lacking. This paper investigates a non-parametric closed-loop behavior learning method for multi-agent motion planning, which underpins a data-driven predictive control framework. Utilizing an innovative methodology with closed-loop input/output measurements of the unknown system, the behavior of the system is learned based on the collected dataset, and thus the constructed non-parametric predictive model can be used to determine the optimal control actions. This non-parametric predictive control framework alleviates the heavy computational burden commonly encountered in the optimization procedures typically in alternate methodologies requiring open-loop input/output measurement data collection and parametric system identification. The proposed data-driven approach is also shown to preserve good robustness properties. Finally, a multi-UAV system is used to demonstrate the highly effective outcome of this promising development.

As a notable machine learning paradigm, the research efforts in the context of reinforcement learning have certainly progressed leaps and bounds. When compared with reinforcement learning methods with the given system model, the methodology of the reinforcement learning architecture based on the unknown model generally exhibits significantly broader universality and applicability. In this work, a new reinforcement learning architecture is developed and presented without the requirement of any prior knowledge of the system model, which is termed as an approach of a "neural network iterative linear quadratic regulator (NNiLQR)". Depending solely on measurement data, this method yields a completely new non-parametric routine for the establishment of the optimal policy (without the necessity of system modeling) through iterative refinements of the neural network system. Rather importantly, this approach significantly outperforms the classical iterative linear quadratic regulator (iLQR) method in terms of the given objective function because of the innovative utilization of further exploration in the methodology. As clearly indicated from the results attained in two illustrative examples, these significant merits of the NNiLQR method are demonstrated rather evidently.