Manipulating objects whose physical properties are unknown remains one of the greatest challenges in robotics. Controlling grasp force is an essential aspect of handling unknown objects without slipping or crushing them. Although extensive research has been carried out on grasp force control, unknown object manipulation is still difficult because conventional approaches assume that object properties (mass, center of gravity, friction coefficient, etc.) are known for grasp force control. One of the approaches to address this issue is incipient slip detection. However, there has been few detailed investigations of robust detection and control of incipient slip on rotational case. This study makes contributions on deriving the theoretical model of incipient slip and proposes a new algorithm to detect incipient slip. Additionally, a novel sensor configuration and a grasp force control algorithm based on the derived theoretical model are proposed. Finally, the proposed algorithm is evaluated by grasping objects with different weights and moments including a fragile pastry (éclair).

Motion planning is important in a wide variety of applications such as robotic manipulation. However, it is still challenging to reliably find a collision-free path within a reasonable time. To address the issue, this paper proposes a novel framework which combines a sampling-based planner and deep learning for faster motion planning, focusing on heuristics. The proposed method extends Task-Space Rapidly-exploring Random Trees (TS-RRT) to guide the trees with a "heuristic map" where every voxel has a cost-to-go value toward the goal. It also utilizes fully convolutional neural networks (CNNs) for producing more appropriate heuristic maps, rather than manually-designed heuristics. To verify the effectiveness of the proposed method, experiments for motion planning using a real environment and mobile manipulator are carried out. The results indicate that it outperforms the existing planners, especially in terms of the average planning time with smaller variance.

This paper proposes a control framework for a two-armed and two-wheeled mobile robot that can coordinate all the joint forces to achieve diverse motion objectives such as position, velocity, acceleration, force and impedance at any part of the body. The framework comprises two components: 1) Generalized Inverse Dynamics (GID) that determines joint forces satisfying multiple objectives considering task priorities and various constraints and 2) the Idealized Joint Unit (IJU) that generates accurate torque with assigned apparent inertia and viscosity. GID treats the robot as a single manipulator with multiple branches using a joint model with 2-DOF motion subspace equivalent to two opposing wheels. A 21-DOF mobile robot equipped with IJUs is set up and GID is applied to it. The result shows that GID works well in the examples of physical human-robot interaction and object manipulation where motion objectives are attained coordinating the whole body while keeping passivity due to the redundancy and the assigned impedance property.

In this paper we propose a new robust force and position control method for property-unknown objects grasping. The proposed control method is capable of selecting the force control or position control, and smooth and quick switching according to the amount of the external force. The proposed method was applied to adaptive grasping by three-fingered hand which has 12 DOF, and the experimental results revealed that the smooth collision process and the stable grasping is realized even if the precise surface position, the mass and the stiffness are unknown. In addition a new algorithm determines the grasp force according to the "slip" measured with the tactile sensor and the viscoelastic media on the fingertip. This algorithm works at starting and stationary state, so the friction and mass unknown object grasping is realized by the effectual force.