We present distributed distance-based control (DDC), a novel approach for controlling a multi-agent system, such that it achieves a desired formation, in a resource-constrained setting. Our controller is fully distributed and only requires local state-estimation and scalar measurements of inter-agent distances. It does not require an external localization system or inter-agent exchange of state information. Our approach uses spatial-predictive control (SPC), to optimize a cost function given strictly in terms of inter-agent distances and the distance to the target location. In DDC, each agent continuously learns and updates a very abstract model of the actual system, in the form of a dictionary of three independent key-value pairs $(\Delta \vec s,\Delta d)$, where ∆d is the partial derivative of the distance measurements along a spatial direction $\Delta \vec s$. This is sufficient for an agent to choose the best next action. We validate our approach by using DDC to control a collection of Crazyflie drones to achieve formation flight and reach a target while maintaining flock formation.

We introduce Spatial Predictive Control (SPC), a technique for solving the following problem: given a collection of robotic agents with black-box positional low-level controllers (PLLCs) and a mission-specific distributed cost function, how can a distributed controller achieve and maintain cost-function minimization without a plant model and only positional observations of the environment? Our fully distributed SPC controller is based strictly on the position of the agent itself and on those of its neighboring agents. This information is used in every time step to compute the gradient of the cost function and to perform a spatial look-ahead to predict the best next target position for the PLLC. Using a simulation environment, we show that SPC outperforms Potential Field Controllers, a related class of controllers, on the drone flocking problem. We also show that SPC works on real hardware, and is therefore able to cope with the potential sim-to-real transfer gap. We demonstrate its performance using as many as 16 Crazyflie 2.1 drones in a number of scenarios, including obstacle avoidance.

World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning world models for high-dimensional observations (e.g., pixel inputs) has become practicable on standard RL benchmarks and some games, their effectiveness in real-world robotics applications has not been explored. In this paper, we investigate how such agents generalize to real-world autonomous vehicle control tasks, where advanced model-free deep RL algorithms fail. In particular, we set up a series of time-lap tasks for an F1TENTH racing robot, equipped with a high-dimensional LiDAR sensor, on a set of test tracks with a gradual increase in their complexity. In this continuous-control setting, we show that model-based agents capable of learning in imagination substantially outperform model-free agents with respect to performance, sample efficiency, successful task completion, and generalization. Moreover, we show that the generalization ability of model-based agents strongly depends on the choice of their observation model. We provide extensive empirical evidence for the effectiveness of world models provided with long enough memory horizons in sim2real tasks.