Vertiencoder: Self-supervised kinodynamic representation learning on vertically challenging terrain

M Nazeri, A Datar, A Pokhrel, C Pan, G Warnell… - arxiv preprint arxiv …, 2024 - arxiv.org
We present VertiEncoder, a self-supervised representation learning approach for robot
mobility on vertically challenging terrain. Using the same pre-training process, VertiEncoder …

Top-nav: Legged navigation integrating terrain, obstacle and proprioception estimation

J Ren, Y Liu, Y Dai, J Long, G Wang - arxiv preprint arxiv:2404.15256, 2024 - arxiv.org
Legged navigation is typically examined within open-world, off-road, and challenging
environments. In these scenarios, estimating external disturbances requires a complex …

Lift, splat, map: Lifting foundation masks for label-free semantic scene completion

A Zhang, R Heijne, J Biswas - arxiv preprint arxiv:2407.03425, 2024 - arxiv.org
Autonomous mobile robots deployed in urban environments must be context-aware, ie, able
to distinguish between different semantic entities, and robust to occlusions. Current …

Robot Navigation Using Physically Grounded Vision-Language Models in Outdoor Environments

M Elnoor, K Weerakoon, G Seneviratne, R **an… - arxiv preprint arxiv …, 2024 - arxiv.org
We present a novel autonomous robot navigation algorithm for outdoor environments that is
capable of handling diverse terrain traversability conditions. Our approach, VLM-GroNav …

Teaching Robots to" Get It Right"

J Biswas - The International FLAIRS Conference Proceedings, 2024 - journals.flvc.org
We are interested in building and deploying service mobile robots to assist with arbitrary end-
user tasks in everyday environments. In such open-world settings, how can we ensure that …