51 citations · 53 across the 7 of their papers we have counts for
7 papers
An Object SLAM Framework for Association, Mapping, and High-Level Tasks
Yanmin Wu, Yunzhou Zhang, Delong Zhu +4
Object SLAM is considered increasingly significant for robot high-level perception and decision-making. Existing studies fall short in terms of data association, object representat…
Self-Supervised Object Goal Navigation with In-Situ Finetuning
So Yeon Min, Yao-Hung Hubert Tsai, Wei Ding +4
A household robot should be able to navigate to target objects without requiring users to first annotate everything in their home. Most current approaches to object navigation do n…
Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agents
Yao-Hung Hubert Tsai, Hanlin Goh, Ali Farhadi +1
The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human…
SAFER: Safe Collision Avoidance using Focused and Efficient Trajectory Search with Reinforcement Learning
Mario Srouji, Hugues Thomas, Hubert Tsai +2
Collision avoidance is key for mobile robots and agents to operate safely in the real world. In this work we present SAFER, an efficient and effective collision avoidance system th…
The Foreseeable Future: Self-Supervised Learning to Predict Dynamic Scenes for Indoor Navigation
Hugues Thomas, Jian Zhang, Timothy D. Barfoot
We present a method for generating, predicting, and using Spatiotemporal Occupancy Grid Maps (SOGM), which embed future semantic information of real dynamic scenes. We present an a…
Learning Spatiotemporal Occupancy Grid Maps for Lifelong Navigation in Dynamic Scenes
Hugues Thomas, Matthieu Gallet de Saint Aurin, Jian Zhang +1
We present a novel method for generating, predicting, and using Spatiotemporal Occupancy Grid Maps (SOGM), which embed future information of dynamic scenes. Our automated generatio…
Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation
Hugues Thomas, Ben Agro, Mona Gridseth +2
We present a self-supervised learning approach for the semantic segmentation of lidar frames. Our method is used to train a deep point cloud segmentation architecture without any h…