Sound can be utilized to gather information about vehicles approaching a Non-Line-of-Sight (NLoS) region that remains hidden from Line-of-Sight (LoS) sensors due to its reflective and diffractive characteristics, like a radar. However, due to the inability to determine the location of NLoS vehicles in previous studies, it has not been possible to construct a sound-based active emergency braking system. This paper introduces a novel approach for localization of vehicles approaching in NLoS regions through sound. Specifically, a new particle filter method incorporating Acoustic-Spatial Pseudo-Likelihood (ASPLE) has been proposed to track objects using both acoustic and spatial information from the ego vehicle. Also, the Acoustic Recognition based Invisible-target Localization (ARIL) dataset, which is the firstly providing the location of the NLoS vehicle as ground truth using Bird’s Eye View camera, is proposed. The proposed method is validated using two datasets: the ARIL dataset and the Occluded Vehicle Acoustic Detection Dataset (OVAD) dataset. The proposed method exhibited remarkable performance in localizing NLoS targets in both datasets, predicting the location of the vehicle in the NLoS region. Lastly, the analysis of how the reflection of sound affects to the proposed method, highlighting variations based on the spatial situations, and demonstrate the empirical convergence of the method is described. Our code and dataset is available athttps://github.com/mingujeon/NLoSVehicleLocalization.

The dynamics of all real quadrotors inevitably differ even if they are the same product. In particular, the dynamics can change significantly during the flight due to additional device attachments or overheating motors. In this study, we focus on training a low-level controller, which operates in response to dynamics-changes without prior knowledge or fine-tuning of the parameters, using reinforcement learning. We randomize the dynamics of quadrotors in the simulator and train the policy based on dynamics information extracted from the state-action history through recurrent neural networks (RNNs). In addition, our experiment demonstrates the difficulties in applying existing actor-critic structures that extract dynamics information using end-to-end RNNs for unstable quadrotors; hence, we propose a novel structure with better performance. Finally, the excellent performance of the proposed controller is verified by testing experiments that stabilize quadrotors with different dynamics. The experiment videos and the code can be found at https://github.com/jackyoung96/RNN-Quadrotor-controller.

Robotic agents trained using reinforcement learning have the problem of taking unreliable actions in an out-of-distribution (OOD) state. Agents can easily become OOD in real-world environments because it is almost impossible for them to visit and learn the entire state space during training. Unfortunately, unreliable actions do not ensure that agents perform their original tasks successfully. Therefore, agents should be able to recognize whether they are in OOD states and learn how to return to the learned state distribution rather than continue to take unreliable actions. In this study, we propose a novel method for retraining agents to recover from OOD situations in a self-supervised manner when they fall into OOD states. Our in-depth experimental results demonstrate that our method substantially improves the agent’s ability to recover from OOD situations in terms of sample efficiency and restoration of the performance for the original tasks. Moreover, we show that our method can retrain the agent to recover from OOD situations even when in-distribution states are difficult to visit through exploration. Code and supplementary materials are available at https://github.com/SNUChanKim/SeRO.