Mobile robot typically has limited on-board resources and may be applied in different indoor environment. Thus, it is necessary that they can learn a map and navigate themselves autonomously with lightweight algorithms. A novel topological map-building-based localization and navigation method is proposed in this paper. Based on the depth curve provided by a 3D sensor, a progressive Bayesian classifier is developed to realize direct corridor type identification. Instead of extracting features from single observation, information from multi-observations are fused to achieve a more robust performance. A topological map generation and loop closing method are proposed to build the environment map through autonomous exploration. Based on the derived map and the Markov localization method, the robot can then localize itself and navigate freely in the indoor environment. Experiments are performed on a recently built mobile robot system, and the results verify the effectiveness of the proposed methodology.

In the high precision robotic assembly processes, the process parameters have to be tuned in order to adapt to variations and satisfy the performance requirements. However, because of the modeling difficulty and low efficiency of the existing solutions, this task is usually performed offline. In this paper, an online parameter optimization method is developed. Gaussian Process Regression(GPR) is utilized to model the relationship between the process parameters and system performance. The GPR surrogated Bayesian Optimization Algorithm(GPRBOA) is proposed to optimize the process parameters. To reduce the risk of converging to a local minimum, a random variation factor is added to the Lower Confidence Bound(LCB) acquisition function to balance the exploration and exploitation processes. To deal with the computational burden of GPR, a switching criterion is proposed to coordinate the optimization process and production process to reduce the computational complexity. Experiments were performed using a peg-in-hole process. The experimental results verify the effectiveness of the proposed algorithm and demonstrate its efficiency and accuracy compared to Design Of Experiment(DOE) methods. The proposed method is the first attempt of model-driven assembly process parameter optimization and will generate big economic impact.

Robot teaching is necessary for the current industrial robot applications. Because work stations have to be stopped to perform teaching processes, the manufacturing efficiency is decreased. In this paper we propose to utilize an uncalibrated vision system mounted on a mobile robot (“Adult” robot) with learning capability to supervise a group of fixed robots (“Child” robots) to accomplish a robot teaching task automatically without stopping work stations. To increase the system flexibility, hand-eye calibration and calibration between the robots are eliminated. A Partial Observable Markov Decision Process(POMDP) is formulated and solved using the Successive Approximation of the Reachable Space under Optimal Policies (SARSOP) algorithm to enable the teaching process using image features with uncertainties. The proposed algorithm was tested using the “adult” robot to teach a “child” robot to perform a high accuracy peg-in-hole assembly process. The experimental results verify the effectiveness of the proposed approach. The proposed method can also be used in other areas to enable robot teaching.

Autonomous Industrial Mobile Manipulators (AIMMs) combine the advantages of both mobile robots and industrial manipulators, therefore they have great mobility, flexibility and functionality. However, great challenges arise when AIMMs are expected to perform various tasks in unstructured or semi-structured environments. Since AIMMs are typically configured in the indoor environments, indoor localization & navigation is one of these challenges. A novel topological indoor localization & navigation method is proposed in this paper. Based on the depth information provided by a popular Kinect sensor, a progressive Bayesian classifier is developed to realize direct corridor type identification. Instead of extracting features from single observation, information from multi-observations are fused to achieve a more robust performance. With the ability of directly determining the corridor types, a topological map generation and loop closing method is proposed to build the environment map through autonomous exploration. By using the Markov Localization and trajectory planning method, the robot can localize itself and navigating freely in the indoor environment. Experiments are performed on a recently built AIMM system, and the results verify the effectiveness of the proposed methodology.

This paper discusses the dynamical servo control problem for the Acrobot - a mechanics with two links while just one actuator applied to the second link. The dynamical servo control aims to access generic points in the state space not just the equilibrium points. Stabilizing of generic points is impossible and a possible way is to stabilize some periodic orbits passing through the desired points. Virtual constraints are used to generate such orbits. By analyzing the integration of the zero dynamics of the Acrobot subjected to virtual constraints, conditions of whether there is an orbit passing through the desired point and the orbit function are found. A cascade control strategy is proposed to stabilize both the virtual constraint and the orbit function which decides the system behavior. Simulation results show the effectiveness of the control law.