Semantically-Aware Strategies for Stereo-Visual Robotic Obstacle Avoidance

TL;DR

This paper introduces a semantically-aware obstacle avoidance system for mobile robots that combines visual segmentation and depth data to improve navigation safety and efficiency in unstructured environments.

Contribution

It presents a novel obstacle avoidance module that integrates semantic object classification with depth sensing, allowing for more intelligent and context-aware navigation decisions.

Findings

System effectively classifies and localizes obstacles using combined visual and depth data.

Navigation efficiency improves by selectively avoiding or approaching obstacles based on their identity.

Validated in simulated terrestrial and underwater environments, demonstrating feasibility.

Abstract

Mobile robots in unstructured, mapless environments must rely on an obstacle avoidance module to navigate safely. The standard avoidance techniques estimate the locations of obstacles with respect to the robot but are unaware of the obstacles' identities. Consequently, the robot cannot take advantage of semantic information about obstacles when making decisions about how to navigate. We propose an obstacle avoidance module that combines visual instance segmentation with a depth map to classify and localize objects in the scene. The system avoids obstacles differentially, based on the identity of the objects: for example, the system is more cautious in response to unpredictable objects such as humans. The system can also navigate closer to harmless obstacles and ignore obstacles that pose no collision danger, enabling it to navigate more efficiently. We validate our approach in two simulated environments: one terrestrial and one underwater. Results indicate that our approach is feasible and can enable more efficient navigation strategies.