The artificial lateral line (ALL), comprising distributed flow sensors, has been successful in sensing motion states of bioinspired underwater robots like robotic fish. However, its application to robots driven by rotating propellers remains unexplored due to the complexity of propeller wake flow. This article investigates the feasibility of using ALL to sense propeller wake for underwater robot leader-follower formation. To estimate the lateral motion states of a leader propeller, this article designs a multioutput deep learning network that extracts temporal and spatial features from distributed pressure measurements of propeller wake. Extensive experiments are conducted on a designed testbed, the results of which validate the effectiveness of the proposed propeller wake sensing method.
9 February 2026 in IEEE Robotics and Automation Letters
The target defense problem (TDP) for unmanned surface vehicles (USVs) concerns intercepting an adversarial USV before it breaches a designated target region, using one or more defending USVs. A particularly challenging scenario arises when the attacker exhibits superior maneuverability compared to the defenders, significantly complicating effective interception. To tackle this challenge, this letter introduces ARBoids, a novel adaptive residual reinforcement learning framework that integrates deep reinforcement learning (DRL) with the biologically inspired, force-based Boids model. Within this framework, the Boids model serves as a computationally efficient baseline policy for multi-agent coordination, while DRL learns a residual policy to adaptively refine and optimize the defenders' actions. The proposed approach is validated in a high-fidelity Gazebo simulation environment, demonstrating superior performance over traditional interception strategies, including pure force-based approaches and vanilla DRL policies. Furthermore, the learned policy exhibits strong adaptability to attackers with diverse maneuverability profiles, highlighting its robustness and generalization capability.
As a new approach to underwater signal acquisition, small-size passive arrays deployed on autonomous underwater vehicles (AUVs) have some performance limitations for DOA estimation. On the one hand, there is the problem of real-time front-end processing; on the other hand, there is the problem of estimation accuracy. Especially when faced with a multi-target problem, too small an angle between the sources and too large an energy difference between the signals can make DOA estimation difficult. This article introduces an improved sparse DOA estimation method for practical multi-objective DOA estimation in complex scenarios of AUV platforms. The main work of this thesis is to introduce a new updating formula in the sparse iterative covariance process, and it will dramatically speed up sparse fitting and somewhat solve the aperture problem for small-size arrays. Compared to other sparse methods, the method completes the DOA estimation more quickly without prior information about the target. Finally, simulations have verified the method’s effectiveness.