Fingertip Contact Force Direction Control using Tactile Feedback

The human hand is an immensely sophisticated tool adept at manipulating and grasping objects of unknown characteristics. Its capability lies in perceiving interaction dynamics through touch and adjusting contact force direction and magnitude to ensure successful manipulation. Despite advancements in control algorithms, sensing technologies, compliance integration, and ongoing research, precise finger force control for dexterous manipulation using tactile sensing remains relatively unexplored.In this work, we explore the challenges related to individual finger contact force control and propose a method for directing such forces perceived through tactile sensing. The proposed method is evaluated using an Allegro hand with Xela tactile sensors. Results are presented and discussed, alongside consideration for potential future improvements.

Speeding up 6-DoF Grasp Sampling with Quality-Diversity

Recent advances in AI have led to significant results in robotic learning, including natural language-conditioned planning and efficient optimization of controllers using generative models. However, the interaction data remains the bottleneck for generalization. Getting data for grasping is a critical challenge, as this skill is required to complete many manipulation tasks. Quality-Diversity (QD) algorithms optimize a set of solutions to get diverse, high-performing solutions to a given problem. This paper investigates how QD can be combined with priors to speed up the generation of diverse grasps poses in simulation compared to standard 6-DoF grasp sampling schemes. Experiments conducted on 4 grippers with 2-to-5 fingers on standard objects show that QD outperforms commonly used methods by a large margin. Further experiments show that QD optimization automatically finds some efficient priors that are usually hard coded. The deployment of generated grasps on a 2-finger gripper and an Allegro hand shows that the diversity produced maintains sim-to-real transferability. We believe these results to be a significant step toward the generation of large datasets that can lead to robust and generalizing robotic grasping policies.