Task-oriented grasping for dexterous robots using postural synergies and reinforcement learning

TL;DR

By combining data-driven insights from human grasping behavior with learning by exploration provided by reinforcement learning, humanoid robots capable of context-aware manipulation actions, can develop humanoid robots capable of context-aware manipulation actions, facilitating collaboration in human-centered environments.

Abstract

In this paper, we address the problem of task-oriented grasping for humanoid robots, emphasizing the need to align with human social norms and task-specific objectives. Existing methods, employ a variety of open-loop and closed-loop approaches but lack an end-to-end solution that can grasp several objects while taking into account the downstream task's constraints. Our proposed approach employs reinforcement learning to enhance task-oriented grasping, prioritizing the post-grasp intention of the agent. We extract human grasp preferences from the ContactPose dataset, and train a hand synergy model based on the Variational Autoencoder (VAE) to imitate the participant's grasping actions. Based on this data, we train an agent able to grasp multiple objects while taking into account distinct post-grasp intentions that are task-specific. By combining data-driven insights from human grasping behavior with learning by exploration provided by reinforcement learning, we can develop humanoid robots capable of context-aware manipulation actions, facilitating collaboration in human-centered environments.

Figures (10)

• Figure 1: Example of different execution of a grasp according to the post-grasp intention as captured in the dataset presented in Brahmbhatt_2020_ECCV. In the left figure, the person grasps the hammer in order to use it, in the right it grasps it in order to hand it over to another person.
• Figure 2: Example grasping targets for hammer extracted from the ContactPose dataset Brahmbhatt_2020_ECCV.
• Figure 3: Proposed agent structure for task-oriented grasping.
• Figure 4: Rewards for training policies with 1) full joint control, 2) PCA synergy space, and 3) VAE synergy space. The thick line is the average among the two seeds and the shaded part denotes the standard deviation.
• Figure 5: Training environment.