Domain Randomization and Generative Models for Robotic Grasping

by   Joshua Tobin, et al.

Deep learning-based robotic grasping has made significant progress the past several years thanks to algorithmic improvements and increased data availability. However, state-of-the-art models are often trained on as few as hundreds or thousands of unique object instances, and as a result generalization can be a challenge. In this work, we explore a novel data generation pipeline for training a deep neural network to perform grasp planning that applies the idea of domain randomization to object synthesis. We generate millions of unique, unrealistic procedurally generated objects, and train a deep neural network to perform grasp planning on these objects. Since the distribution of successful grasps for a given object can be highly multimodal, we propose an autoregressive grasp planning model that maps sensor inputs of a scene to a probability distribution p_θ, where p_θ (g | I) corresponds to the model's estimate of the normalized probability of success of the grasp g conditioned on the observations I. Our model allows us to sample grasps efficiently at test time (or avoid sampling entirely). We evaluate our model architecture and data generation pipeline in simulation and find we can achieve >90% success rate on previously unseen realistic objects at test time despite having only been trained on random objects.


page 1

page 3

page 6


Towards Precise Model-free Robotic Grasping with Sim-to-Real Transfer Learning

Precise robotic grasping of several novel objects is a huge challenge in...

Learning Grasp Ability Enhancement through Deep Shape Generation

Data-driven especially deep learning-based approaches have become a domi...

Multi-Fingered Grasp Planning via Inference in Deep Neural Networks

We propose a novel approach to multi-fingered grasp planning leveraging ...

Evaluating Gaussian Grasp Maps for Generative Grasping Models

Generalising robotic grasping to previously unseen objects is a key task...

Planning Multi-Fingered Grasps as Probabilistic Inference in a Learned Deep Network

We propose a novel approach to multi-fingered grasp planning leveraging ...

Learning Mobile Manipulation

Providing mobile robots with the ability to manipulate objects has, desp...

Online Tool Selection with Learned Grasp Prediction Models

Deep learning-based grasp prediction models have become an industry stan...

Please sign up or login with your details

Forgot password? Click here to reset