15 accepted papers
In cluttered environments where rigid and deformable objects coexist, collision-free paths often do not exist. Planners that enforce collision-free trajectories therefore perform poorly by excluding feasible contact-aware trajectories. We introduce the deformation-guided acceptable-contact motion pl
Aerial docking of unmanned aerial vehicles (UAVs) is essential for advanced applications like persistent surveillance and in-flight recharging. Conventional underactuated multirotors, with only four control inputs for six degrees of freedom, lack independent control over their full pose. This fundam
Reinforcement Learning (RL) with Group Relative Policy Optimization (GRPO) shows great promise for enhancing LLM reasoning, but remains challenged by sparse and unstable rewards in long-horizon tasks. Existing approaches to reward shaping struggle to balance semantic expressiveness, reliability, and…
This letter presents a novel weakly supervised semantic segmentation method for radar segmentation, where the existing LiDAR semantic segmentation models are employed to generate semantic labels, which then serve as supervision signals for training a radar semantic segmentation model. The obtained r
Structural coupling and complex environments bring challenges to the precision movement of gantry multi-axis systems in industrial production. In particular, ensuring the transient and steady-state performance of the gantry system under dynamic loads is a difficult problem to be addressed. This lett
This letter focuses on the accuracy of LiDAR-inertial odometry (LIO). We propose a novel high-precision tightly-coupled LIO method, SI-LIO, based on the invariant extended Kalman filter with a single-iteration estimate update. This method utilizes the Lie exponential map between the matrix Lie group
Reinforcement learning (RL) for robotics poses significant consideration of safety during training. However, a major challenge of safe reinforcement learning (SRL) methods is the curse of dimensionality. Although existing SRL methods utilizing dimensionality reduction (DR) approaches could provide s
Addressing safe and efficient navigation in dynamic, realistic, and complex environments stands as a pivotal inquiry within the realm of robotics. Recently, numerous learning-based methods are introduced into the field of navigation, yielding notable outcomes. In this letter, we propose a hierarchic…
Integrating Large Language Models (LLMs) into robotics significantly enhances autonomous task planning. However, ensuring that multi-step task plans (action sequence) generated by LLMs comply with pre-defined safety constraints during planning and execution remains a challenge, limiting their adapta…
The role of a motion planner is pivotal in quadrotor applications, yet existing methods often struggle to adapt to complex environments, limiting their ability to achieve fast, safe, and robust flight. In this letter, we introduce a performance-enhanced quadrotor motion planner designed for autonomo
For real-world navigation, it is important to endow robots with the capabilities to navigate safely and efficiently in a complex environment with both dynamic and static obstacles. However, achieving path-finding in non-convex complex environments without maps as well as enabling multiple robots to
Visual servoing of Unmanned Aerial Vehicles (UAVs) has achieved satisfactory performance in fixed and planar motion targets. Due to highly coupled system dynamics and the sensitivity of the target image to aircraft attitude, the problem for chasing free-flying targets remains challenging. In this pa
A main challenge restricting the application of control barrier functions (CBFs) to complex scenarios is the absence of robustness against uncertainties induced by both measurements of the environment and robot dynamics. In this letter, we propose an uncertainty-aware, learning-based approach to con
Learning driving policies using an end-to-end network has been proved a promising solution for autonomous driving. Due to the lack of a benchmark driver behavior dataset that contains both the visual and the LiDAR data, existing works solely focus on learning driving from visual sensors. Besides, mo…
Recent works have proved that combining spatial and temporal visual cues can significantly improve the performance of various vision-based robotic systems. However, for the ultrasonic sensors used in most robotic tasks (e.g. collision avoidance, localization and navigation), there is a lack of bench…