Technology Category
Intelligent Robots: ManipulationMachine Learning: Imitation Learning & Inverse Reinforcement LearningSearch and Optimization: Sampling/Simulation-based Search
Sensorized gripper for human demonstrations
🤖 AI Summary
To address the complexity and heavy reliance on manual teleoperation in robot programming for unstructured environments, this paper proposes a compliant assembly learning method from few human demonstrations. We employ a sensorized commercial gripper to collect “box-in-box” assembly demonstrations and design a Cartesian-space motion generation framework that jointly optimizes end-effector pose and joint configurations to enhance dexterity. Motion-force coupling patterns are modeled using Gaussian Mixture Models (GMM), integrated with real-time impedance control for environment adaptation. Evaluated in real-world settings, the method achieves over 95% stable assembly success rate using only a few brief demonstrations. It significantly lowers the programming barrier for unstructured tasks and establishes a reproducible technical pathway for lightweight, low-sample imitation learning.
Technology Category
Application Category
📝 Abstract
Ease of programming is a key factor in making robots ubiquitous in unstructured environments. In this work, we present a sensorized gripper built with off-the-shelf parts, used to record human demonstrations of a box in box assembly task. With very few trials of short interval timings each, we show that a robot can repeat the task successfully. We adopt a Cartesian approach to robot motion generation by computing the joint space solution while concurrently solving for the optimal robot position, to maximise manipulability. The statistics of the human demonstration are extracted using Gaussian Mixture Models (GMM) and the robot is commanded using impedance control.
Problem
Research questions and friction points this paper is trying to address.
Develops sensorized gripper for human demonstrations.
Enables robots to perform tasks with minimal trials.
Uses GMM and impedance control for robot task execution.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Sensorized gripper with off-the-shelf parts
Cartesian motion generation for optimal positioning
GMM and impedance control for task replication
🔎 Similar Papers
No similar papers found.
