10 papers
Legs Over Arms: On the Predictive Value of Lower-Body Pose for Human Trajectory Prediction from Egocentric Robot Perception
Nhat Le, Daeun Song, Xuesu Xiao
Predicting human trajectory is crucial for social robot navigation in crowded environments. While most existing approaches treat human as point mass, we present a study on multi-ag…
MAction-SocialNav: Multi-Action Socially Compliant Navigation via Reasoning-enhanced Prompt Tuning
Zishuo Wang, Xinyu Zhang, Zhuonan Liu +4
Socially compliant navigation requires robots to move safely and appropriately in human-centered environments by respecting social norms. However, social norms are often ambiguous,…
MOSU: Autonomous Long-range Robot Navigation with Multi-modal Scene Understanding
Jing Liang, Kasun Weerakoon, Daeun Song +3
We present MOSU, a novel autonomous long-range navigation system that enhances global navigation for mobile robots through multimodal perception and on-road scene understanding. MO…
Narrate2Nav: Real-Time Visual Navigation with Implicit Language Reasoning in Human-Centric Environments
Amirreza Payandeh, Anuj Pokhrel, Daeun Song +2
Large Vision-Language Models (VLMs) have demonstrated potential in enhancing mobile robot navigation in human-centric environments by understanding contextual cues, human intention…
McARL:Morphology-Control-Aware Reinforcement Learning for Generalizable Quadrupedal Locomotion
Prakhar Mishra, Amir Hossain Raj, Xuesu Xiao +1
We present Morphology-Control-Aware Reinforcement Learning (McARL), a new approach to overcome challenges of hyperparameter tuning and transfer loss, enabling generalizable locomot…
HACL: History-Aware Curriculum Learning for Fast Locomotion
Prakhar Mishra, Amir Hossain Raj, Xuesu Xiao +1
We address the problem of agile and rapid locomotion, a key characteristic of quadrupedal and bipedal robots. We present a new algorithm that maintains stability and generates high…