CAREER: Controlling Ecologically Destructive Processes with a Network of Intelligent Robotic Agents

Stanford University, Stanford CA

Investigators

Abstract

This project aims to control destructive environmental processes such as forest fires, oil spills, and agricultural pest infestations through the intelligent, coordinated intervention of a group of robots. This requires the development of fundamentally new control theoretic and algorithmic tools to drive the robots to take control actions to regulate the environmental process. The robots' control actions close a large-scale feedback loop around the robots and the environment, giving rise to complex dynamical phenomena. The project proposes control strategies for this coupled robot-environment system in three different timescale regimes: (i) the environment changes slowly compared to the robots' dynamics, (ii) the environment and robot dynamics are on the same timescale and immediate control effect is sought, and (iii) the environment and robot dynamics are on the same timescale and long-term control effect is sought. Three different optimization based techniques are proposed to generate decentralized control strategies for each regime. Stability, convergence, and optimality properties of the robot-environment system under these strategies are studied. Furthermore, experiments with a network of quadrotor aerial robots, both in the lab and outdoors, demonstrate the practicality of the control strategies. The project also incorporates a comprehensive education and outreach program using quadrotor robots as teaching tools to reach students from diverse backgrounds at all grade levels. Ultimately, the project seeks to alleviate the economic, social, and ecological damage caused by oil and other chemical spills, forest fires, pest infestations, and other ecologically destructive phenomena by laying the foundations of a new robotic technology.