Tactile Grasp Refinement using Deep Reinforcement Learning and Analytic Grasp Stability Metrics

09/23/2021
by   Alexander Koenig, et al.
11

Reward functions are at the heart of every reinforcement learning (RL) algorithm. In robotic grasping, rewards are often complex and manually engineered functions that do not rely on well-justified physical models from grasp analysis. This work demonstrates that analytic grasp stability metrics constitute powerful optimization objectives for RL algorithms that refine grasps on a three-fingered hand using only tactile and joint position information. We outperform a binary-reward baseline by 42.9 combination of geometric and force-agnostic grasp stability metrics yields the highest average success rates of 95.4 62.3 rotational errors between 0 and 14 degrees. In a second experiment, we show that grasp refinement algorithms trained with contact feedback (contact positions, normals, and forces) perform up to 6.6 receives no tactile information.

READ FULL TEXT

page 1

page 3

page 4

page 6

research
01/18/2019

TactileGCN: A Graph Convolutional Network for Predicting Grasp Stability with Tactile Sensors

Tactile sensors provide useful contact data during the interaction with ...
research
10/09/2019

Towards Learning to Detect and Predict Contact Events on Vision-based Tactile Sensors

In essence, successful grasp boils down to correct responses to multiple...
research
05/28/2018

More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch

For humans, the process of grasping an object relies heavily on rich tac...
research
09/10/2019

MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning

Vision-based grasping systems typically adopt an open-loop execution of ...
research
03/05/2018

Tactile Regrasp: Grasp Adjustments via Simulated Tactile Transformations

This paper presents a novel regrasp control policy that makes use of tac...
research
06/04/2018

Passive Static Equilibrium with Frictional Contacts and Application to Grasp Stability Analysis

This paper studies the problem of passive grasp stability under an exter...
research
04/04/2023

Online augmentation of learned grasp sequence policies for more adaptable and data-efficient in-hand manipulation

When using a tool, the grasps used for picking it up, reposing, and hold...

Please sign up or login with your details

Forgot password? Click here to reset