Distributed Graph Algorithms for Robotics

Important links: Schedule, Accepted Contributions

At several scales in robotics, there are good reasons to distribute computation across graphs. Networks of many robots need to coordinate or collaborate, with peer-to-peer mesh communication preferable to a single master hub for robustness, scalability and security.  Or a single complex robot could gain efficiency, low latency and modularity by locating multiple graph-connected processing units close to its multiple actuators and sensors. At the smallest scale, new graph processor chips enable internal distribution of storage and processing across many cores connected in flexible patterns, promising high throughput and low power usage.

At all scales, while computing becomes more distributed, the goals of computation usually remain global.  A robot team may have the joint goal of providing efficient coverage of an area; or a graph processor implements a vision algorithm to estimate the motion of a single robot. This workshop will therefore focus on the emerging research area of algorithms which can compute global properties via distributed computation.  Researchers are currently investigating many different types of distributed algorithms, for varied tasks such as inference, planning or learning, but we believe that there is a timely opportunity to attempt to distill common principles.

The following questions and topics will be discussed in the workshop:

• Distributed computation patterns

• Message passing schedules

• Belief Propagation

• Many robot systems

• Distributed localisation

• Distributed SLAM

• Distributed planning / MPC

• Communication protocols

• Image processing on processor arrays

• Graph processors and other novel multi-core hardware

• Self-organising systems

• Cellular automata for robotics

• Federated learning

• Sensor networks

• Continual learning on graphs

All authors and participants need to register through ICRA 2023 here.

ICRA London 2023

ExCel London

Royal Victoria Dock

1 Western Gateway

London, E16 1XL