42 citations · 50 across the 14 of their papers we have counts for
16 papers
MoMo: Dial Motion Mode in Robot Manipulation with Spatiotemporal Action Tokenization
Yuhan Hu, Hugues Thomas, Peide Huang +3
To operate effectively across diverse contexts, robots must not only perform manipulation tasks accurately but also adapt how their actions unfold to the task, object, and interact…
Pts3D-LLM: Studying the Impact of Token Structure for 3D Scene Understanding With Large Language Models
Hugues Thomas, Chen Chen, Jian Zhang
Effectively representing 3D scenes for Multimodal Large Language Models (MLLMs) is crucial yet challenging. Existing approaches commonly only rely on 2D image features and use vari…
DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation
James R. Han, Hugues Thomas, Jian Zhang +2
How can a robot safely navigate around people with complex motion patterns? Deep Reinforcement Learning (DRL) in simulation holds some promise, but much prior work relies on simula…
MakeWay: Object-Aware Costmaps for Proactive Indoor Navigation Using LiDAR
Binbin Xu, Allen Tao, Hugues Thomas +2
In this paper, we introduce a LiDAR-based robot navigation system, based on novel object-aware affordance-based costmaps. Utilizing a 3D object detection network, our system identi…
KPConvX: Modernizing Kernel Point Convolution with Kernel Attention
Hugues Thomas, Yao-Hung Hubert Tsai, Timothy D. Barfoot +1
In the field of deep point cloud understanding, KPConv is a unique architecture that uses kernel points to locate convolutional weights in space, instead of relying on Multi-Layer…
Embedding Pose Graph, Enabling 3D Foundation Model Capabilities with a Compact Representation
Hugues Thomas, Mouli Sivapurapu, Jian Zhang
This paper presents the Embedding Pose Graph (EPG), an innovative method that combines the strengths of foundation models with a simple 3D representation suitable for robotics appl…
Human Following in Mobile Platforms with Person Re-Identification
Mario Srouji, Yao-Hung Hubert Tsai, Hugues Thomas +1
Human following is a crucial feature of human-robot interaction, yet it poses numerous challenges to mobile agents in real-world scenarios. Some major hurdles are that the target p…
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…
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
Meida Chen, Qingyong Hu, Zifan Yu +6
Although various 3D datasets with different functions and scales have been proposed recently, it remains challenging for individuals to complete the whole pipeline of large-scale d…
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…
Unsupervised Learning of Lidar Features for Use in a Probabilistic Trajectory Estimator
David J. Yoon, Haowei Zhang, Mona Gridseth +2
We present unsupervised parameter learning in a Gaussian variational inference setting that combines classic trajectory estimation for mobile robots with deep learning for rich sen…
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…
Rotation-Invariant Point Convolution With Multiple Equivariant Alignments
Hugues Thomas
Recent attempts at introducing rotation invariance or equivariance in 3D deep learning approaches have shown promising results, but these methods still struggle to reach the perfor…
KPConv: Flexible and Deformable Convolution for Point Clouds
Hugues Thomas, Charles R. Qi, Jean-Emmanuel Deschaud +3
We present Kernel Point Convolution (KPConv), a new design of point convolution, i.e. that operates on point clouds without any intermediate representation. The convolution weights…
Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods
Hugues Thomas, Jean-Emmanuel Deschaud, Beatriz Marcotegui +2
This paper introduces a new definition of multiscale neighborhoods in 3D point clouds. This definition, based on spherical neighborhoods and proportional subsampling, allows the co…