Abstract:

The main objective of this thesis is to develop an autonomous navigation system for robot arms, which can operate in most of environments, such as kitchen, factory, etc. Furthermore, by extending our planner into a dual-arm planner, we can enhance the work efficiency of the robot.
To begin with, we propose an algorithm about motion planning in the state space. It can overcome some difficult planning problems in static environments. Due to the anytime planning fashion, the partial plan can also be returned when deliberation time is limited. Further, the Multi-RRTs algorithm uses this advantage of continuously re-planning to adjust the parameters.

Next, in order to solve the problem of planning in the dynamic environments, we proposed a CT-RRTs (Bi-direction RRTs in Configuration Time space) planner, which can make the robot arm reach goal successfully in the partially known dynamic environment. However it plans in the augmented state-time space of robot arm configuration and the positions of moving objects. Various techniques are used to accelerate planning and enhance its safety.

Finally, we utilize the new planner to develop the dual-arm planner, and it can be used as the basis to solve higher level problems in motion planning.

A software platform is developed for both simulation and for real-world navigation, where environment and planning results are visualized in 3D. In real-world implementation, a vision module for distance measurement and a motor control module are integrated. In our experiments, the system is able to navigate the robot arm in static environments in real time.