Structure from silence: Learning scene structure from ambient sound

Z Chen, X Hu, A Owens - ar** Field
Y He, S Xu, JX Zhong, S Shin, N Trigoni… - ar** field for
spatial acoustic effects prediction in an acoustic 3D space with a single stationary audio …

Learning to Map Efficiently by Active Echolocation

X Hu, S Purushwalkam, D Harwath… - 2023 IEEE/RSJ …, 2023 - ieeexplore.ieee.org
Using visual SLAM to map new environments requires time-consuming visits to all regions
for data collection. We propose an approach to estimate maps of areas beyond the visible …

Latent Object Characteristics Recognition with Visual to Haptic-Audio Cross-modal Transfer Learning

N Saito, J Moura, H Uchida, S Vijayakumar - arxiv preprint arxiv …, 2024 - arxiv.org
Recognising the characteristics of objects while a robot handles them is crucial for adjusting
motions that ensure stable and efficient interactions with containers. Ahead of realising …

WildFusion: Multimodal Implicit 3D Reconstructions in the Wild

Y Liu, B Chen - arxiv preprint arxiv:2409.19904, 2024 - arxiv.org
We propose WildFusion, a novel approach for 3D scene reconstruction in unstructured, in-
the-wild environments using multimodal implicit neural representations. WildFusion …

SonicBoom: Contact Localization Using Array of Microphones

M Lee, U Yoo, J Oh, J Ichnowski, G Kantor… - arxiv preprint arxiv …, 2024 - arxiv.org
In cluttered environments where visual sensors encounter heavy occlusion, such as in
agricultural settings, tactile signals can provide crucial spatial information for the robot to …

SoundNeRirF: Receiver-to-Receiver Sound Neural Room Impulse Response Field

Y He, JX Zhong, Z Dai, N Trigoni, A Markham - openreview.net
We present SoundNeRirF, a framework that learns a continuous receiver-to-receiver neural
room impulse response field~(r2r-RIR) to help robot efficiently predict the sound to be heard …