Autonomous multi-agent search and rescue: algorithms and experiments
Details
Speakers
Autonomous multi-agent search and rescue: algorithms and experiments
The technological capabilities for components of autonomous vehicles are ever increasing, with continual advances in the capabilities of their sensor suites and computational resources. With these resources, they can perceive and analyze the world around them. However, for the vehicles to autonomously exploit these resources, their guidance algorithms must go beyond following sequences of waypoints. They must safely and reliably sense, interpret, and react to uncertain knowledge by making useful measurements to acquire the necessary information.
This work presents an algorithmic approach and experimental flight results for autonomous search and rescue using multiple unmanned aerial vehicles (UAVs), an application focused on acquiring information that can benefit greatly from automation and optimization. An information-seeking guidance system was developed for mobile sensor networks, combining information theoretic control with decentralized collision avoidance to yield an agile, scalable algorithm. This algorithm is applied in simulation to three sensing modalities, and demonstrated in experiments with quadrotor helicopters on the most complicated sensing modality of the three, sensing the magnetic field of avalanche rescue beacons. The guidance system exploits a model of the interaction between the sensing and control actions of the vehicles to optimize the rate at which information is acquired. Non-parametric estimators, particle filters, are used to directly estimate the information available for any observation the sensors could make. Techniques for distributed control of mobile sensor networks are proposed using information approximation and collision avoidance laws.
This approach yields an integrated online UAV system with collision avoidance and multi-aircraft mission-planning and coordination. The guidance system algorithmic design, real-time implementation, and experimental results are presented. The results demonstrate the ability to localize a beacon with a single operator supervising multiple UAVs.
Additional information
Our work is centered around a series of Focus Areas that we believe are the future of science and technology.
We’re continually developing new technologies, many of which are available for Commercialization.
PARC scientists and staffers are active members and contributors to the science and technology communities.