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

2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)(2019)

引用 15|浏览1
暂无评分
摘要
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.
更多
查看译文
关键词
inference time,probabilistic multimodal actor models,vision-based robotic grasping,neural density model,neural network,normalizing flows,complex probability distributions,Gaussian mixture,conditional distribution,4 dimensional action space
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要