Existing robotic musicians utilize detailed handcrafted instrument models to generate or learn policies for playing because model-free or inaccurate policy rollouts might easily damage or wear out fragile instruments. We introduce an approach to characterize geometric models of chordophones and their audio onset responses directly through audio-tactile exploration with a physical robot arm. Initially, the system refines prior estimates of string positions, provided by kinesthetic teaching or visual estimation, through repeated attempts to pluck individual strings. A subsequent stage implements a Safe Active Exploration paradigm based on Gaussian Processes to explore and characterize the audio onset response of feasible plucking motions while minimizing invalid attempts. The resulting models can be used to actuate an imprecise robotic arm to play sequences of notes with varying loudness on a Chinese Guzheng.

Visual sensor modalities dominate traditional robot calibration, but when environment contacts are relevant, the tactile modality can provide another natural, accurate, and highly relevant modality. Most existing tactile sensing methods for robot calibration are constrained to specific sensor-object pairs, limiting their applicability. This paper pioneers a general approach to exploit contacts in robot calibration, supporting self-touch throughout the entire system kinematics by generalizing touchable surfaces to any accurately represented mesh surface. The approach supports different contact sensors as long as a simple single-contact interface can be provided. Integrated into the Atomic Transformation Optimization Method (ATOM) calibration methodology, our work facilitates seamless integration of both modalities in a single approach. Our results demonstrate comparable performance to single-modality calibration but can trade off accuracy between both modalities, thus increasing overall robustness. Furthermore, we observe that utilizing a touch point at the end of a kinematic chain slightly improves calibration over touching the chain links with an external sensor but find no significant advantage of restricting touch to end-effector contacts when calibrating a dual-arm system with our method.

Planar pushing remains a challenging research topic, where building the dynamic model of the interaction is the core issue. Even an accurate analytical dynamic model is inherently unstable because physics parameters such as inertia and friction can only be approximated. Data-driven models usually rely on large amounts of training data, but data collection is time consuming when working with real robots.In this paper, we collect all training data in a physics simulator and build an LSTM-based model to fit the pushing dynamics. Domain Randomization is applied to capture the pushing trajectories of a generalized class of objects. When executed on the real robot, the trained recursive model adapts to the tracked object's real dynamics within a few steps. We propose the algorithm Recurrent Model Predictive Path Integral (RMPPI) as a variation of the original MPPI approach, employing state-dependent recurrent models. As a comparison, we also train a Deep Deterministic Policy Gradient (DDPG) network as a model-free baseline, which is also used as the action generator in the data collection phase. During policy training, Hindsight Experience Replay is used to improve exploration efficiency. Pushing experiments on our UR5 platform demonstrate the model's adaptability and the effectiveness of the proposed framework.

Established indoor robot navigation frameworks build on the separation between global and local planners. Whereas global planners rely on traditional graph search algorithms, local planners are expected to handle driving dynamics and resolve minor conflicts. We present a system to train neural-network policies for such a local planner component, explicitly accounting for humans navigating the space. DRL-agents are trained in randomized virtual 2D environments with simulated human interaction. The trained agents can be deployed as a drop-in replacement for other local planners and significantly improve on traditional implementations. Performance is demonstrated on a MiR-100 transport robot.

A lot of motion planning research in robotics focuses on efficient means to find trajectories between individual start and goal regions, but it remains challenging to specify and plan robotic manipulation actions which consist of multiple interdependent subtasks. The Task Constructor framework we present in this work provides a flexible and transparent way to define and plan such actions, enhancing the capabilities of the popular robotic manipulation framework MoveIt!.11The Task Constructor framework is publicly available at https://github.com/ros-planning/moveit_task_constructor Subproblems are solved in isolation in black-box planning stages and a common interface is used to pass solution hypotheses between stages. The framework enables the hierarchical organization of basic stages using containers, allowing for sequential as well as parallel compositions. The flexibility of the framework is illustrated in multiple scenarios performed on various robot platforms, including bimanual ones.

In this paper, we present TeachNet, a novel neural network architecture for intuitive and markerless vision-based teleoperation of dexterous robotic hands. Robot joint angles are directly generated from depth images of the human hand that produce visually similar robot hand poses in an end-to-end fashion. The special structure of TeachNet, combined with a consistency loss function, handles the differences in appearance and anatomy between human and robotic hands. A synchronized human-robot training set is generated from an existing dataset of labeled depth images of the human hand and simulated depth images of a robotic hand. The final training set includes 400K pairwise depth images and joint angles of a Shadow C6 robotic hand. The network evaluation results verify the superiority of TeachNet, especially regarding the high-precision condition. Imitation experiments and grasp tasks teleoperated by novice users demonstrate that TeachNet is more reliable and faster than the state-of-the-art vision-based teleoperation method.

In this paper, we propose an end-to-end grasp evaluation model to address the challenging problem of localizing robot grasp configurations directly from the point cloud. Compared to recent grasp evaluation metrics that are based on handcrafted depth features and a convolutional neural network (CNN), our proposed PointNetGPD is lightweight and can directly process the 3D point cloud that locates within the gripper for grasp evaluation. Taking the raw point cloud as input, our proposed grasp evaluation network can capture the complex geometric structure of the contact area between the gripper and the object even if the point cloud is very sparse. To further improve our proposed model, we generate a large-scale grasp dataset with 350k real point cloud and grasps with the YCB object set for training. The performance of the proposed model is quantitatively measured both in simulation and on robotic hardware. Experiments on object grasping and clutter removal show that our proposed model generalizes well to novel objects and outperforms state-of-the-art methods. Code and video are available at https://lianghongzhuo.github.io/PointNetGPD.

Mixed reality (MR)opens up new vistas for human-robot interaction (HRI)scenarios in which a human operator can control and collaborate with co-located robots. For instance, when using a see-through head-mounted-display (HMD)such as the Microsoft HoloLens, the operator can see the real robots and additional virtual information can be superimposed over the real-world view to improve security, acceptability and predictability in HRI situations. In particular, previewing potential robot actions in-situ before they are executed has enormous potential to reduce the risks of damaging the system or injuring the human operator. In this paper, we introduce the concept and implementation of such an MR human-robot collaboration system in which a human can intuitively and naturally control a co-located industrial robot arm for pick-and-place tasks. In addition, we compared two different, multimodal HRI techniques to select the pick location on a target object using (i)head orientation (aka heading)or (ii)pointing, both in combination with speech. The results show that heading-based interaction techniques are more precise, require less time and are perceived as less physically, temporally and mentally demanding for MR-based pick-and-place scenarios. We confirmed these results in an additional usability study in a delivery-service task with a multi-robot system. The developed MR interface shows a preview of the current robot programming to the operator, e. g., pick selection or trajectory. The findings provide important implications for the design of future MR setups.