Grasp detection methods typically target the detection of a set of free-floating hand poses that can grasp the object. However, not all of the detected grasp poses are executable due to physical constraints. Even though it is straightforward to filter invalid grasp poses in the post-process, such a two-staged approach is computationally inefficient, especially when the constraint is hard. In this work, we propose an approach to take the following two constraints into account during the grasp detection stage, namely, (i) the picked object must be able to be placed with a predefined configuration without in-hand manipulation (ii) it must be reachable by the robot under the joint limit and collision-avoidance constraints for both pick and place cases. Our key idea is to train an SE(3) grasp diffusion network to estimate the noise in the form of spatial velocity, and constrain the denoising process by a multi-target differential inverse kinematics with an inequality constraint, so that the states are guaranteed to be reachable and placement can be performed without collision. In addition to an improved success ratio, we experimentally confirmed that our approach is more efficient and consistent in computation time compared to a naive two-stage approach.

This paper addresses the challenging problem of category-level pose estimation. Current state-of-the-art methods for this task face challenges when dealing with symmetric objects and when attempting to generalize to new environments solely through synthetic data training. In this work, we address these challenges by proposing a probabilistic model that relies on diffusion to estimate dense canonical maps crucial for recovering partial object shapes as well as establishing correspondences essential for pose estimation. Furthermore, we introduce critical components to enhance performance by leveraging the strength of the diffusion models with multi-modal input representations. We demonstrate the effectiveness of our method by testing it on a range of real datasets. Despite being trained solely on our generated synthetic data, our approach achieves state-of-the-art performance and unprecedented generalization qualities, outperforming baselines, even those specifically trained on the target domain. Our code and data for the generalization benchmark can be found at https://woven-planet.github.io/DiffusionNOCS/.

Learning-based grasp detectors typically assume a precision grasp, where each finger only has one contact point, and estimate the grasp probability. In this work, we propose a data generation and learning pipeline that can leverage power grasping, which has more contact points with an enveloping configuration and is robust against both positioning error and force disturbance. To train a grasp detector to prioritize power grasping while still keeping precision grasping as the secondary choice, we propose to train the network against the magnitude of disturbance in the gravity direction a grasp can resist (gravity-rejection score) rather than the binary classification of success. We also provide an efficient data generation pipeline for a dataset with gravity-rejection score annotation. Evaluation in both simulation and real-robot clarifies the significant improvement in our approach, especially when the objects are heavy.

In this paper, we present a robotic device for mouse tail vein injection. We propose a mouse holding mechanism to realize vein injection without anesthetizing the mouse, which consists of a tourniquet, vacuum port, and adaptive tail-end fixture. The position of the target vein in 3D space is reconstructed from a high-resolution stereo vision. The vein is detected by a simple but robust vein line detector. Thanks to the proposed two-staged calibration process, the total time for the injection process is limited to 1.5 minutes, despite that the position of needle and tail vein varies for each trial. We performed an injection experiment targeting 40 mice and succeeded to inject saline to 37 of them, resulting 92.5% success ratio.

This paper describes a stable knee-stretched walking of a humanoid by the resolved viscoelasticity control (RVC). The RVC method resolves multiple viscoelasticities in task-space, including the center of mass viscoelasticity for balancing, into joint-space viscoelasticity. Although a robust and compliant motion was achieved by the RVC method in previous studies, the conventional knee-bent posture to avoid the kinematic singularity suffered large knee joint torque. In this study, we propose an extension of the RVC capable of the kinematic singularity. We demonstrate through simulations and experiments that the RVC method considering the singularity achieves a stable and human-like walking, reducing the knee joint torque and improving the energy efficiency.

For heavy duty tasks which are needed in field or rough terrain, we developed a hydrostatically actuated anthropomorphic hand. The hand is specifically designed for the humanoid robot HYDRA, whose 40 joints are driven by back-drivable electro-hydrostatic actuators (EHA). Each designed hand has four fingers with a total of five DOF. Each finger has three joints underactuated by one tendon. Opposition/reposition of the thumb joint is also driven by one tendon. The five tendons are pulled by a miniature linear cluster EHA mounted in the forearm. The cluster EHA consists of a light weight tie-rod cylinder cluster with five pistons, and five low friction trochoid pumps with a crescent separator. Its 300 N nominal tension generates 1.5 Nm joint torque on each of the finger joints. Design of the cylinder and pump, with results of evaluation experiments is shown in this paper. Forearm structure with a mechanism to measure the tendon tension, low friction tendon routing in the forearm, low friction wire guiding link for the wrist, and parallel link wrist driving mechanism with two EHAs are also described.