Learning Probabilistic Multi-Modal Actor Models for Vision-Based Robotic Grasping

04/15/2019
by   Mengyuan Yan, et al.
0

Many previous works approach vision-based robotic grasping by training a value network that evaluates grasp proposals. These approaches require an optimization process at run-time to infer the best action from the value network. As a result, the inference time grows exponentially as the dimension of action space increases. We propose an alternative method, by directly training a neural density model to approximate the conditional distribution of successful grasp poses from the input images. We construct a neural network that combines Gaussian mixture and normalizing flows, which is able to represent multi-modal, complex probability distributions. We demonstrate on both simulation and real robot that the proposed actor model achieves similar performance compared to the value network using the Cross-Entropy Method (CEM) for inference, on top-down grasping with a 4 dimensional action space. Our actor model reduces the inference time by 3 times compared to the state-of-the-art CEM method. We believe that actor models will play an important role when scaling up these approaches to higher dimensional action spaces.

READ FULL TEXT

page 1

page 5

page 6

research
05/29/2020

Multi-modal Transfer Learning for Grasping Transparent and Specular Objects

State-of-the-art object grasping methods rely on depth sensing to plan r...
research
10/22/2018

Actor-Expert: A Framework for using Action-Value Methods in Continuous Action Spaces

Value-based approaches can be difficult to use in continuous action spac...
research
08/22/2023

Vision-Based Intelligent Robot Grasping Using Sparse Neural Network

In the modern era of Deep Learning, network parameters play a vital role...
research
10/01/2019

Quantile QT-Opt for Risk-Aware Vision-Based Robotic Grasping

The distributional perspective on reinforcement learning (RL) has given ...
research
02/24/2019

Vision Based Picking System for Automatic Express Package Dispatching

This paper presents a vision based robotic system to handle the picking ...
research
09/17/2018

Vision-based Teleoperation of Shadow Dexterous Hand using End-to-End Deep Neural Network

In this paper, we present TeachNet, a novel neural network architecture ...
research
04/18/2023

Implicit representation priors meet Riemannian geometry for Bayesian robotic grasping

Robotic grasping in highly noisy environments presents complex challenge...

Please sign up or login with your details

Forgot password? Click here to reset