BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation

R Shah, A Yu, Y Zhu, Y Zhu, R Martín-Martín - arXiv preprint arXiv …, 2024 - arxiv.org
To operate at a building scale, service robots must perform very long-horizon mobile
manipulation tasks by navigating to different rooms, accessing different floors, and …

HEIGHT: Heterogeneous Interaction Graph Transformer for Robot Navigation in Crowded and Constrained Environments

S Liu, H Xia, FC Pouria, K Hong, N Chakraborty… - arXiv preprint arXiv …, 2024 - arxiv.org
We study the problem of robot navigation in dense and interactive crowds with
environmental constraints such as corridors and furniture. Previous methods fail to consider …

[PDF][PDF] Structured Interaction Models for Robot Learning in Human Spaces

S Liu - shuijing725.github.io
Robots are becoming increasingly capable of performing tasks in isolation. However, how to
operate them in human environments remains an open challenge. Subtle and highly …