The morphological properties of dexterous soft hands offer many advantages in the accomplishment of contact-rich manipulation tasks. Nevertheless, classical analytic and learning-based approaches are not directly applicable because they were developed with a rigid hand paradigm for manipulation in mind.
To meet this challenge, we want to develop control strategies that exploit the compliance of the hand in contact scenarios. This requires an understanding of the morphological computation (MC) the hand is performing in manipulation tasks. Given a measure for MC, we want to find control-sequences that exploit the beneficial MC of the hand. By beneficial, we refer to MC that supports/facilitates in-hand manipulation. Bringing together the computation performed by the hand and the computation performed by a controller, we hope to discover "funnels" for in-hand manipulation that represent robust, repeatable and sequencable manipulation skills.
This effort will include investigations of different feature encodings, sample-efficient learning algorithms, appropriate simulation environments and various kinds of hand sensorization.
We present in-hand manipulation skills on a dexterous, compliant, anthropomorphic hand. Even though these skills were derived in a simplistic manner, they exhibit surprising robustness to variations in shape, size, weight, and placement of the manipulated object. The are also very insensitive in variation of execution speeds, ranging from highly dynamic to quasi-static. The robustness of the skills leads to compositional properties that enable extended and robust manipulation programs. To explain the surprising robustness of the in-hand manipulation skills, we performed a detailed, empirical analysis of the skills’ performance. From this analysis, we derive three principles that we believe to be an important foundation for robust robotic in-hand manipulation, and possibly for manipulation in general.
Bitte beachten Sie: Sobald Sie sich das Video ansehen, werden Informationen darüber an YouTube/Google übermittelt. Weitere Informationen dazu finden Sie unter Google Privacy.
This paper presents a feedback-control framework for in-hand manipulation (IHM) with dexterous soft hands that enables the acquisition of manipulation skills in the real-world within minutes. We choose the deformation state of the soft hand as the control variable. To control for a desired deformation state, we use coarsely approximated Jacobians of the actuation-deformation dynamics. These Jacobians are obtained via explorative actions. This is enabled by the self-stabilizing properties of compliant hands, which allow us to use linear feedback control in the presence of complex contact dynamics. To evaluate the effectiveness of our approach, we show the generalization capabilities for a learned manipulation skill to variations in object size by 100 %, 360 degree changes in palm inclination and to disabling up to 50 % of the involved actuators. In addition, complex manipulations can be obtained by sequencing such feedback-skills.
We present a simple approach to in-hand cube reconfiguration. By simplifying planning, control, and perception as much as possible, while maintaining robust and general performance, we gain insights into the inherent complexity of in-hand cube reconfiguration. We also demonstrate the effectiveness of combining GOFAI-based planning with the exploitation of environmental constraints and inherently compliant end-effectors in the context of dexterous manipulation. The proposed system outperforms a substantially more complex system for cube reconfiguration based on deep learning and accurate physical simulation, contributing arguments to the discussion about what the most promising approach to general manipulation might be. Project website: https://rbo.gitlab-pages.tu-berlin.de/robotics/simpleIHM/