Jointly learning trajectory generation and hitting point prediction in robot table tennis

Rozo

2019 International Conference on Robotics and Automation (ICRA)

et al. 2019

Self Cite

Unstructured environments impose several challenges when robots are required to perform different tasks and adapt to unseen situations. In this context, a relevant problem arises: how can robots learn to perform various tasks and adapt to different conditions? A potential solution is to endow robots with learning capabilities. In this line, imitation learning emerges as an intuitive way to teach robots different motor skills. This learning approach typically mimics human demonstrations by extracting invariant motion patterns and subsequently applies these patterns to new situations. In this paper, we propose a novel kernel treatment of imitation learning, which endows the robot with imitative and adaptive capabilities. In particular, due to the kernel treatment, the proposed approach is capable of learning human skills associated with high-dimensional inputs. Furthermore, we study a new concept of correlation-adaptive imitation learning, which allows for the adaptation of correlations exhibited in high-dimensional demonstrated skills. Several toy examples and a collaborative task with a real robot are provided to verify the effectiveness of our approach.

Section: Introductionmentioning

confidence: 99%

Non-parametric Imitation Learning of Robot Motor Skills

Rozo

2019 International Conference on Robotics and Automation (ICRA)

et al. 2019

Self Cite

“…In the past few years, imitation learning has been studied in a myriad of applications, such as pouring tasks [1], striking motions [2] and obstacle avoidance [3]. While many approaches focus on skill learning in either Cartesian space or joint space, an important problem arises: can robots imitate human skills in both Cartesian and joint spaces simultaneously?…”

Section: Introductionmentioning

confidence: 99%

Towards Minimal Intervention Control with Competing Constraints

2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Caldwell

2018

Self Cite

As many imitation learning algorithms focus on pure trajectory generation in either Cartesian space or joint space, the problem of considering competing trajectory constraints from both spaces still presents several challenges. In particular, when perturbations are applied to the robot, the underlying controller should take into account the importance of each space for the task execution, and compute the control effort accordingly. However, no such controller formulation exists. In this paper, we provide a minimal intervention control strategy that simultaneously addresses the problems of optimal control and competing constraints between Cartesian and joint spaces. In light of the inconsistency between Cartesian and joint constraints, we exploit the robot null space from an informationtheory perspective so as to reduce the corresponding conflict. An optimal solution to the aforementioned controller is derived and furthermore a connection to the classical finite horizon linear quadratic regulator (LQR) is provided. Finally, a writing task in a simulated robot verifies the effectiveness of our approach.

“…While imitation learning in a single space has achieved reliable performance, the simultaneous learning of skills in both spaces (which we refer to as hybrid space learning) has not been sufficiently investigated yet. In order to illustrate the importance of this hybrid approach, let us consider a robot table tennis task [4], where a racket is attached to the end-effector of an anthropomorphic robot arm. The preliminary goal is to control the racket (being held by the robot end-effector) so as to return the ball towards the human opponent side.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Probabilistic Trajectory Optimization Using Null-Space Exploration

2018 IEEE International Conference on Robotics and Automation (ICRA)

Rozo

2018

Self Cite

In the context of learning from demonstration, human examples are usually imitated in either Cartesian or joint space. However, this treatment might result in undesired movement trajectories in either space. This is particularly important for motion skills such as striking, which typically imposes motion constraints in both spaces. In order to address this issue, we consider a probabilistic formulation of dynamic movement primitives, and apply it to adapt trajectories in Cartesian and joint spaces simultaneously. The probabilistic treatment allows the robot to capture the variability of multiple demonstrations and facilitates the mixture of trajectory constraints from both spaces. In addition to this proposed hybrid space learning, the robot often needs to consider additional constraints such as motion smoothness and joint limits. On the basis of Jacobianbased inverse kinematics, we propose to exploit robot null-space so as to unify trajectory constraints from Cartesian and joint spaces while satisfying additional constraints. Evaluations of hand-shaking and striking tasks carried out with a humanoid robot demonstrate the applicability of our approach.