Fast and accurate segmentation of stroke lesions is highly desirable to help specialists in lesion measurements and making treatment plans. Segmentation of stroke lesions are challenging due to evolvement of stroke, low contrast and highly variable grayscale distributions. In this paper, we propose a novel multi-task learning framework to achieve enhanced segmentation of stroke lesions. In this framework, without increasing the inference time and model parameters in the inference phase, we perform supervised learning on a main task (stroke lesion segmentation) and an auxiliary task (edge segmentation of the brain lesion) to improve the performance of the main task. For validation, a CT brain infarction dataset has been constructed. In terms of the Dice coefficient, the proposed method could enhance at least 4.76% on the constructed CT dataset, and at least 7.97% on the open source dataset Anatomical Tracings of Lesions After Stroke than state-of-the-art models.

The minimum traveling time of a rigid body along a specified geometric path can be achieved by switching between extremal allowable accelerations. A linear programming (LP) problem is formulated to obtain such extreme accelerations for a body handled by multiple robotic manipulators or robotic fingers. Both rigid grasping and grasping with point contacts have been treated.>

A study is made of the so-called slide motions between developable ruled surfaces with the line contact under spatial motion. In particular, the authors consider instantaneous time-based kinematics, which includes the contact speeds and rates of change along reference curves on the surfaces, the velocity, acceleration, and jerk of a reference point on the moving surface, and the constraints on the angular velocity and angular acceleration for maintaining line contact. The derived kinematic relationships can be applied to robotic path planning and actual motion calculations in the presence of a tactile sensor to measure the relative motion at the contact line.>

A new version of the AL language system has been implemented, with emphasis on the specifications for an object's motion in operational space under trajectory planning, and flexible grasping. This paper discusses specifications of object geometry, Cartesian trajectory, control frame calculation from the trajectory and geometry, and motion constraints with respect to the control frame. A simple inverse of a Jacobian matrix linking the control frame to joint space variables is also presented.

This paper is an extension to the 3-dimensional case of our previous work on planar motion with point contact [2]. Here we study the so called roll-slide spatial motions. Such motions occur whenever point contact between bodies is maintained under spatial motion. We consider instantaneous time-based kinematics and assume the presence of a tactile sensor to measure the relative motion at the point of contact. It is indicated how the derived kinematic relationships can be applied to sensor based robotic path planning.