Overcoming Obstructions via Bandwidth-Limited Multi-Agent Spatial Handshaking

TL;DR

This paper introduces MASH, a learnable multi-agent network that enables bandwidth-efficient, obstruction-resilient collaborative perception in robotic swarms by processing raw images directly for improved semantic segmentation.

Contribution

The paper presents MASH, a novel end-to-end learnable network for multi-agent perception that operates on raw images without extra pose or depth data, improving performance under occlusions.

Findings

Achieves 11% IoU improvement over baselines.

Effective in bandwidth-limited, obstruction-prone environments.

Operates solely on raw image data without additional inputs.

Abstract

In this paper, we address bandwidth-limited and obstruction-prone collaborative perception, specifically in the context of multi-agent semantic segmentation. This setting presents several key challenges, including processing and exchanging unregistered robotic swarm imagery. To be successful, solutions must effectively leverage multiple non-static and intermittently-overlapping RGB perspectives, while heeding bandwidth constraints and overcoming unwanted foreground obstructions. As such, we propose an end-to-end learn-able Multi-Agent Spatial Handshaking network (MASH) to process, compress, and propagate visual information across a robotic swarm. Our distributed communication module operates directly (and exclusively) on raw image data, without additional input requirements such as pose, depth, or warping data. We demonstrate superior performance of our model compared against several baselines in a photo-realistic multi-robot AirSim environment, especially in the presence of image occlusions. Our method achieves an absolute 11% IoU improvement over strong baselines.