The work presented here is a preliminary study on the feasibility for using the output of a Generalized Labeled Multi-Bernoulli filter as inputs to online imitation learning via Deep Inverse Reinforcement learning with the end goal of predicting the next states of each trajectory output from the filter. This work samples the labeled state trajectories from the filter and discretizes them to create episodes for learning. It is assumed the multi-target dynamics are unknown, but they are stochastic and act to maximize some unknown reward function. Because the ultimate goal is predicting the multi-target motion using only observations of the targets, Deep Q-learning is used to learn the dynamics. However, as this algorithm depends on the unknown reward function, Deep Inverse Reinforcement learning is used to learn the rewards. Due to the coupled nature of the learning problems, their solutions are iterated in an alternating fashion and upon reaching convergence, future states can be predicted over a given time horizon. The results are preliminary, and many extensions to this work are outlined.

This paper describes a technique for the autonomous mission planning of robotic swarms in high risk environments where agent disablement is likely. Given a swarm operating in a known area, a central command system generates measurements from the swarm. If those measurements indicate changes to the mission situation such as target movement or agent loss, the swarm planning is updated to reflect the new situation and guidance updates are broadcast to the swarm. The primary algorithms featured in this work are A* pathfinding and the Generalized Labeled Multi-Bernoulli multi-object tracking method.

This paper describes a technique for the autonomous mission planning of unmanned aerial system swarms. Given a swarm operating in a known area, a central command system generates measurements from the swarm. If those measurements indicate changes to the mission situation such as target movement, the swarm planning is updated to reflect the new situation and guidance updates are broadcast to the swarm. The primary algorithms featured in this work are A* pathfinding and the Generalized Labeled Multi-Bernoulli multi-target tracking method.

A cost function is constructed for the random finite-set-based swarm guidance problem mechanized by Gaussian mixtures. This cost function uses an automated problem-dependent scaling and introduces an activator function for quadratic convergence of far off Gaussians. The cost function also depends on a target planner to transform user-defined waypoints into “way-areas” by calculating a covariance matrix. These covariances are based upon the given distribution of the target/reference geometry. Then an extended linear-quadratic regulator (LQR) is defined for the swarm problem as an improvement to the iterative LQR (ILQR). The algorithm is tested in a software simulation, and it is found to have easier tuning than ILQR and generates smooth trajectories toward the targets.

A hierarchical structure for Guidance, Navigation, and Control (GNC) of high cardinality teams is proposed. This hierarchy separates the team behavior from the individual agent's GNC and provides an end-to-end framework for the GNC system. It makes use of a central observer/command center to observe all agents and calculate team/group behavior. Random finite set theory is used by the observer to model the team and provide an abstraction from the individual agents by grouping them into Gaussians. This abstraction is a key part of the proposed hierarchy, and allows scalability to high cardinality teams. Additionally, an automated mission planner is designed for optimal group target assignment and trajectory optimization. The combined hierarchy and mission planner are tested against three scenarios, beginning with a simple case of equal targets, groups, and desired distributions of agents, up to unequal desired distributions, group obstacles, and agent death. The algorithm is shown to provide the desired team behavior while separating actions implementable by agents and actions implementable by a central observer.

An ultrawide-band radar system was developed to measure snow thickness from an airborne platform. It is a second-generation device, improving upon a system that was deployed to Antarctica in 2018-2019. The radar operates from 2.7-10.7 GHz and from 10-18 GHz for a theoretical resolution of less than 2 cm. It was deployed to the Grand Mesa National Forest in Colorado on a Twin Otter DHC-6 aircraft in March of 2019. The system successfully mapped the air-snow and snow-ground interfaces as well as some internal layering over both vegetative and non-vegetative areas. In this paper, we discuss the design, development and deployment of this radar and show some preliminary results.