Navigation amongst densely packed crowds remains a challenge for mobile robots. The complexity increases further if the environment layout changes, making the prior computed global plan infeasible. In this paper, we show that it is possible to dramatically enhance crowd navigation by just improving the local planner. Our approach combines generative modelling with inference-time optimization to generate sophisticated long-horizon local plans at interactive rates. More specifically, we train a Vector Quantized Variational AutoEncoder to learn a prior over the expert trajectory distribution conditioned on the perception input. At run-time, this is used as an initialization for a sampling-based optimizer for further refinement. Our approach does not require any sophisticated prediction of dynamic obstacles and yet provides state-of-theart performance. In particular, we compare against the recent DRL-VO approach [2] and show a 40% improvement in success rate and a 6% improvement in travel time.

Most commercially available fixed-wing aerial vehicles (FWV) can carry only small, lightweight computing hardware such as Jetson TX2 onboard. Solving non-linear trajectory optimization on these computing resources is computationally challenging even while considering only the kinematic motion model. Most importantly, the computation time increases sharply as the environment becomes more cluttered. In this paper, we take a step towards overcoming this bottleneck and propose a trajectory optimizer that achieves online performance on both conventional laptops/desktops and Jetson TX2 in a typical urban environment setting. Our optimizer builds on the novel insight that the seemingly non-linear trajectory optimization problem for FWV has an implicit multi-convex structure. Our optimizer exploits these computational structures by bringing together diverse concepts from Alternating Minimization, Bregman iteration, and Alternating Direction Method of Multipliers. We show that our optimizer outperforms the state-of-the-art implementation of sequential quadratic programming approach in optimal control solver ACADO in computation time and solution quality measured in terms of control and goal reaching cost.

Trajectory optimization problems under affine motion model and convex cost function are often solved through the convex-concave procedure (CCP), wherein the non-convex collision avoidance constraints are replaced with its affine approximation. Although mathematically rigorous, CCP has some critical limitations. First, it requires a collision-free initial guess of solution trajectory which is difficult to obtain, especially in dynamic environments. Second, at each iteration, CCP involves solving a convex constrained optimization problem which becomes prohibitive for real-time computation even with a moderate number of obstacles, if long planning horizons are used.In this paper, we propose a novel trajectory optimizer which like CCP involves solving convex optimization problems but can work with an arbitrary initial guess. Moreover, the proposed optimizer can be computationally upto a few orders of magnitude faster than CCP while achieving similar or better optimal cost. The reduced computation time, in turn, stems from some interesting mathematical structures in the optimizer which allows for distributed computation and obtaining solutions in symbolic form. We validate our claims on difficult benchmarks consisting of static and dynamic obstacles.