EROAS: 3D Efficient Reactive Obstacle Avoidance System for Autonomous Underwater Vehicles using 2.5D Forward-Looking Sonar

TL;DR

EROAS tackles safe, efficient autonomous navigation for AUVs under partial observability by augmenting a 2D forward-looking sonar with a pivoting mechanism to create 2.5D perception. It couples three components—SPD2C for fast gap-based decisions, SCG for short-term obstacle memory, and ST-CBF to enforce spatio-temporal safety constraints—into a lightweight, real-time loop that outputs safe reference commands. The approach yields shorter trajectories, reduced travel times, and smoother control than traditional methods like DWA and APF, demonstrated through simulations and hardware-in-the-loop on edge devices. This framework offers a practical, low-computation solution for robust 3D obstacle avoidance in cluttered underwater environments, with potential for edge deployment and future enhancements via global planning and SLAM integration.

Abstract

Autonomous Underwater Vehicles (AUVs) have advanced significantly in obstacle detection and path planning through sonar, cameras, and learning-based methods. However, safe and efficient navigation in cluttered environments remains challenging due to partial observability, turbidity, the limited field-of-view of forward-looking sonar (FLS), and occlusions that obscure obstacle geometry. To address these issues, we propose the Efficient Reactive Obstacle Avoidance Strategy (EROAS), a lightweight framework that augments a standard 2D FLS with a pivoting mechanism, effectively transforming it into a cost-efficient \emph{2.5D sonar}. This design provides vertical information on demand, extending situational awareness while minimizing computational overhead. EROAS integrates three complementary modules: first, Sonar Profile-guided Directional Decision Control (SPD2C) for rapid gap detection and generation of reference commands in both horizontal and vertical planes. Secondly, the Spatial Context Generator (SCG), which maintains a short-term obstacle memory of the past to mitigate partial observability, and finally, a Spatio-Temporal Control Barrier Function (ST-CBF) that enforces forward-invariance of safety constraints by filtering nominal references. Together, these components enable robust, reactive avoidance of obstacles in uncertain and cluttered 3D underwater settings. Simulation and hardware-in-the-loop (HIL) experiments validate the efficacy of the proposed EROAS algorithm, demonstrating improved trajectory efficiency, reduced travel time, and enhanced safety compared to conventional methods such as the Dynamic Window Approach (DWA) and Artificial Potential Fields (APF). https://github.com/AIRLabIISc/EROAS

Figures (8)

• Figure 1: Details of single beam of FLS choi2021physics.
• Figure 2: AUV navigating in cluttered environment
• Figure 3: Schematic of EROAS framework.
• Figure 4: Spatial Context Generator
• Figure 5: Top view of AUV navigating through a 3D environment in Gazebo.