Publications

This paper presents GmClass, a non-visual classifier that utilizes the force feedback from robot-granules interaction, transforms the force sequences into the frequency domain, and integrates them with high-dimensional textual information within a two-branch architecture for multimodal supervised contrastive learning (MSCL).

In this paper, we propose a useful method to estimate the relative distribution of granular material (GM) properties merely from the video of GM-probe interaction.

To the best of our knowledge, it is the first study that employs the Graph Neural Network (GNN) to solve the forward kinematics (FK) problem for Cable-Driven Parallel Robots (CDPRs).

In this paper, we propose a simple yet effective proximity sensing system for underground stuff based on the haptic feedback of the sensor-granules interaction.

In this work, we present One Fling to Goal, an algorithm capable of handling fabric pieces with diverse shapes and physical properties across various scenarios.

This paper presents NeuPAN: a real-time, highly-accurate, map-free, robot-agnostic, and environment-invariant robot navigation solution.

A soft tactile sensor w/ a two-layered weaved polymer-based optical fiber anisotropic structure embedded in a soft elastomer.

In this work, we first formulate the problem of robotic water scooping using goal-conditioned reinforcement learning.

Detection of buried objects beneath granules in advance based on the study of proximity sensing.

In this letter, we present an accelerated collision-free motion planner, namely regularized dual alternating direction method of multipliers (RDA for short), for the model predictive control (MPC) based motion planning problem.

GCCD-PT: a continuous collision detection method that works in UAVs/AGVs/CDPRs.

In this letter, we propose a distributed approach, RL-RVO, for multi-robot navigation combining reciprocal velocity obstacle (RVO) and deep reinforcement learning (DRL) to solve the reciprocal collision avoidance problem under limited information.

A centralized planner w/ low computational burden to schedule multiple AGVs/mobile robots at the intersection of polynomial curves.

A ray-based method to check interference-free condition (IFC) and wrench-closure condition (WCC) along the given polynomial paths for cable-driven parallel robots (CDPRs).

This thesis studies the interference-free workspace (IFW) of arbitrary cable-driven robots (CDRs) for both cables and obstacles using ray-based method, followed by the point-to-point path planning and verification technique to ensure that the resulting motion is within the workspace.