Social robots are expected to adapt to their users and, like their human counterparts, learn from the interaction. In our previous work, we proposed an interactive learning framework that enables a user to intervene and modify a segment of the robot arm trajectory. The framework uses gesture teleoperation and reinforcement learning to learn new motions. In the current work, we compared the user...

In this work a library for solving manipulator motion planning problems has been developed and an algorithm for imposing Cartesian constraints in single arm and dual arm operation has been proposed. The main algorithm is based on RRT [1]. The code has been tested with several single arm and dual arm robots. Our method is able to find collision free paths in environments occupied with obstacles....

although construction has been known as a highly complex application field for autonomous robotic systems, recent advances in this field offer great hope for using robotic capabilities to develop automated construction. today, space research agencies seek to build infrastructures without human intervention, and construction companies look to robots with the potential to improve construction qua...

Performing daily interaction tasks such as opening doors and pulling drawers in unstructured environments is a challenging problem for robots. The emergence of soft-bodied robots brings new perspective to solving this problem. In paper, inspired by humans performing through simple behaviors, we propose hierarchical control system soft arms, which the low-level controller achieves motion arm tip...

To achieve multiple obstacle avoidance tasks consisting of zero-space and terminal with self-avoidance permission, we propose an algorithm for dual-arm robots. First, design a self-obstacle gradient optimization function to implement the task between two arms robots by using pseudo-distance as basis collision judgment. Second, is implemented applying adaptive velocity. Third, realized virtual r...