This paper develops a decentralized approach to mobile sensor coverage by a multi-robot system. We consider a scenario where a team of robots with limited sensing range must position itself to effectively detect events of interest in a region characterized by areas of varying importance. Towards this end, we develop a decentralized control policy for the robots-realized via a Graph Neural Network-which uses inter-robot communication to leverage non-local information for control decisions. By explicitly sharing information between multi-hop neighbors, the decentralized controller achieves a higher quality of coverage when compared to classical approaches that do not communicate and leverage only local information available to each robot. Simulated experiments demonstrate the efficacy of multi-hop communication for multi-robot coverage and evaluate the scalability and transferability of the learning-based controllers.

Search-based planning with motion primitives is a powerful motion planning technique that can provide dynamic feasibility, optimality, and real-time computation times on size, weight, and power-constrained platforms in unstructured environments. However, optimal design of the motion planning graph, while crucial to the performance of the planner, has not been a main focus of prior work. This paper proposes to address this by introducing a method of choosing vertices and edges in a motion primitive graph that is grounded in sampling theory and leads to theoretical guarantees on planner completeness. By minimizing dispersion of the graph vertices in the metric space induced by trajectory cost, we optimally cover the space of feasible trajectories with our motion primitive graph. In comparison with baseline motion primitives defined by uniform input space sampling, our motion primitive graphs have lower dispersion, find a plan with fewer iterations of the graph search, and have only one parameter to tune.

This paper investigates servicing waypoints in a wide area using collaborative deployments of vehicles with heterogeneous range and mobility constraints. We formulate a joint planning problem for a single transport truck and multiple service drones in which the truck is constrained to a road and must deploy a team of range-constrained drones to visit waypoints. The need to deploy, collect, and redeploy drones over multiple flights introduces both route finding and scheduling aspects to this problem. We solve large problem instances by decoupling our approach into a service drone route finding phase and a transport truck scheduling phase. Numerical simulations explore the qualitative character of the driving schedule and the quantitative marginal value of adding additional drones to the team as a function of agent number and relative speed. The combination of road network constraints and range constraints make this problem especially relevant to wide area forestry, last-mile delivery, and ecological monitoring applications.

Many algorithms for control of multi-robot teams operate under the assumption that low-latency, global state information necessary to coordinate agent actions can readily be disseminated among the team. However, in harsh environments with no existing communication infrastructure, robots must form ad-hoc networks, forcing the team to operate in a distributed fashion. To overcome this challenge, we propose a task-agnostic, decentralized, low-latency method for data distribution in ad-hoc networks using Graph Neural Networks (GNN). Our approach enables multi-agent algorithms based on global state information to function by ensuring it is available at each robot. To do this, agents glean information about the topology of the network from packet transmissions and feed it to a GNN running locally which instructs the agent when and where to transmit the latest state information. We train the distributed GNN communication policies via reinforcement learning using the average Age of Information as the reward function and show that it improves training stability compared to task-specific reward functions. Our approach performs favorably compared to industry-standard methods for data distribution such as random flooding and round robin. We also show that the trained policies generalize to larger teams of both static and mobile agents.

The multi-robot coverage problem is an essential building block for systems that perform tasks like inspection, exploration, or search and rescue. We discretize the coverage problem to induce a spatial graph of locations and represent robots as nodes in the graph. Then, we train a Graph Neural Network controller that leverages the spatial equivariance of the task to imitate an expert open-loop routing solution. This approach generalizes well to much larger maps and larger teams that are intractable for the expert. In particular, the model generalizes effectively to a simulation of ten quadrotors and dozens of buildings in an urban setting. We also demonstrate the GNN controller can surpass planning-based approaches in an exploration task.

We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication. We quantify the amount of communication as the maximum degree of the communication graph; this metric captures settings where agents have limited bandwidth. Minimizing communication is challenging due to the combinatorial nature of both the decision space and the objective; for instance, we cannot solve this problem by training neural networks using gradient descent. We propose a novel algorithm that synthesizes a control policy that combines a programmatic communication policy used to generate the communication graph with a transformer policy network used to choose actions. Our algorithm first trains the transformer policy, which implicitly generates a "soft" communication graph; then, it synthesizes a programmatic communication policy that "hardens" this graph, forming a neurosymbolic transformer. Our experiments demonstrate how our approach can synthesize policies that generate low-degree communication graphs while maintaining near-optimal performance.

Effective communication is required for teams of robots to solve sophisticated collaborative tasks. In practice it is typical for both the encoding and semantics of communication to be manually defined by an expert; this is true regardless of whether the behaviors themselves are bespoke, optimization based, or learned. We present an agent architecture and training methodology using neural networks to learn task-oriented communication semantics based on the example of a communication-unaware expert policy. A perimeter defense game illustrates the system's ability to handle dynamically changing numbers of agents and its graceful degradation in performance as communication constraints are tightened or the expert's observability assumptions are broken.

Micro air vehicles exemplified by quadrotors generate downward thrust in their body fixed frame and may only maneuver spatially by changing their orientation. As a result of this underactuation they are fundamentally incapable of simultaneously regulating orientation and position. Furthermore, their feasible maneuvers are limited to spatial trajectories with continuously differentiable acceleration. We present a coaxial helicopter which emulates full actuation over forces and torques (six degrees of freedom) using only two actuators. The orientation of the thrust vector from each rotor is governed by the drive motor by exciting a cyclic flapping response in special articulated blades. The useful separation of orientation and translation dynamics is demonstrated in flight experiments by tracking spatial trajectories while maintaining flat body attitude as well as tracking desired orientations near hover while station keeping.

We present the control design, system integration, and free flight evaluation of a novel 227 g swashplateless coaxial helicopter. This micro aerial vehicle (MAV) achieves authority over roll, pitch, and yaw orientation as well as maneuvering thrust using only two propellers directly affixed to two motors. No additional aerodynamic control surfaces or actuators are introduced. Instead, cyclic control is obtained through the underactuated dynamic response of the main rotor itself to a modulated drive torque. Comparisons are drawn to conventional four-motor quadrotors and four-actuator fixed pitch coaxial helicopters in terms of mechanical complexity and actuator mass fraction. Trim power consumption in hover is reported across a range of symmetric and asymmetric loading states. Closed loop trajectory tracking maneuvers are demonstrated in a motion capture environment.

We present the methodology, algorithms, system design, and experiments addressing the self-assembly of large teams of autonomous robotic boats into floating platforms. Identical self-propelled robotic boats autonomously dock together and form connected structures with controllable variable stiffness. These structures can self-reconfigure into arbitrary shapes limited only by the number of rectangular elements assembled in brick-like patterns. An O(m2) complexity algorithm automatically generates assembly plans which maximize opportunities for parallelism while constructing operator-specified target configurations with m components. The system further features an O(n3) complexity algorithm for the concurrent assignment and planning of trajectories from n free robots to the growing structure. Such peer-to-peer assembly among modular robots compares favorably to a single active element assembling passive components in terms of both construction rate and potential robustness through redundancy. We describe hardware and software techniques to facilitate reliable docking of elements in the presence of estimation and actuation errors, and we consider how these local variable stiffness connections may be used to control the structural properties of the larger assembly. Assembly experiments validate these ideas in a fleet of 0.5 m long modular robotic boats with onboard thrusters, active connectors, and embedded computers.

This paper addresses the self-assembly of a large team of autonomous boats into floating platforms. We describe the design of individual boats, the systems concept, the algorithms, the software architecture and experimental results with prototypes that are 1:12 scale realizations of modified ISO shipping containers, with the goal of demonstrating self-assembly into large maritime structures such as air strips, bridges, harbors or sea bases. Each container is a robotic module capable of holonomic motion that can dock in a brick pattern to form arbitrary shapes. Over 60 modules were built of varying capability. The docking mechanism is designed to be robust to large disturbances that can be expected in the high seas. The docking mechanism also incorporates adjustable stiffness so that the conglomerate can comply to waves representative of sea state three, and have the ability to dynamically stiffen as required. The component modules for autonomous assembly, docking and simultaneous collision-free planning as well as the software architecture are presented along with the description of experimental verification.

Traditional coaxial helicopter micro air vehicles use a large propeller motor in conjunction with two small servomotors to control thrust, pitch, and roll forces and moments. Quadrotors similarly generate these necessary forces and moments through the coordinated control of multiple actuators. We present a novel propeller architecture which allows a single motor and rotor to express such control by modulating the torque applied to one passively hinged, underactuated propeller. Flight tests of a two-motor coaxial helicopter demonstrate that such a system can provide active stability and control in a real flight system.