Fei-Yue Wang

Stereo camera calibration without absolute-world-coordinate information

A technique for calibrating stereo cameras to determine their relative rotations and translations without using absolute position information from external world reference points is proposed. The main idea is to calculate these rotations and translations using a single camera calibration method through a virtual world coordinate system. In this way the stereo camera calibration can be carried out using three reference points of known relative positions on the plane formed by the three points. In addition, we decompose the calibration equations into two groups. The first involves only relative rotational parameters, while the second deals only with translational parameters which can be solved analytically once the rotational parameters have been found. Extensive numerical simulations have shown that the proposed calibration technique is very robust.

Experimental robotic excavation with fuzzy logic and neural networks

This paper describes experimental results for autonomous robotic rock excavation with fuzzy logic and neural networks. An excavation goal is decomposed into several tasks, whereas a take is accomplished by executing appropriate excavation behaviors. Finally, a behavior is carried out by a sequence of primitive, machine executing excavation actions. Excavation goals, tasks, and behaviors are specified using finite state machines (FSM) based on excavation heuristics and expertise from skilled human operators. The decision making in the FSMs are implemented using neural networks which are capable of improving their performance from previous task executions. Excavation actions are given using fuzzy logic rules acquired from human experience and heuristics. Several experiments are presented that demonstrate the systems ability to complete required excavation tasks effectively.

A cell mapping method for general optimum trajectory planning of multiple robotic arms

Abstract This paper proposes a method that uses cell state space and cell mapping based techniques for planning general optimum trajectories along given geometric paths for coordinated multiple robotic arm systems. The major advantages of this method include its simplicity and applicability to a wide range of problem formulations. In particular, three performance indices for optimum trajectory specification are investigated, i.e., minimum-energy, minimum-jerk, and minimum-time formulations. A simple search strategy is constructed using cell-to-cell mapping to find optimum trajectories. A special feature of this search algorithm is its ability to generate all optimum trajectories for all possible initial conditions through a single search. The computational complexity is analyzed for the search algorithm and its hierarchical implementation. Parallel execution of the hierarchical search method is discussed and the results indicate that it can improve the cell-mapping search efficiency significantly.

A fuzzy control system for an automated mining excavator

To automate a mining excavator the control issues resulting from environmental uncertainties must be solved. In particular the interactions between the excavation tool and the excavation environment are dynamic, unstructured and complex. Thus, generating rigorous mathematical models as required by conventional control techniques is extremely difficult if possible. This paper presents an excavator controller that uses fuzzy logic to interpret forces and torques gathered from a wrist mounted force/torque sensor during the excavation process. This approach enables the transfer of human heuristics and expert knowledge to the controller. Experimental results from several excavation tests using the fuzzy logic controller are given. These results represent the first step toward an integrated approach that uses force/torque, vision, and other sensor data to perform generic tasks in uncertain mining environments.<<ETX>>

A robotic vision system for object identification and manipulation using synergetic pattern recognition

Abstract This paper discusses the application of the synergetic pattern recognition method to a robotic vision system for workpiece identification and manipulation in automated flexible manufacturing environments. The original synergetic algorithm is extended to allow its pattern attention parameters to have different values. Stability analysis of the extended recognition model indicates that the prototype patterns are the only stable patterns and undesired spurious patterns cannot exist. A simple scheme for tuning attention parameters is developed. Simulation results show that the number of object misclassification is reduced significantly with this extension. In addition, an image preprocessing procedure enables synergetic recognition to be simultaneously invariant to spatial pattern translation, rotation, and scaling; while an approach for recovering position, orientation, and size information is also proposed. Simple and efficient task-directed and object-specific strategies for robotic workpiece manipulation are now easy to implement based on these results and procedures.

Optimal construction and control of flexible manipulators : a case study based on LQR output feedback

A mechatronic approach is studied here to design the mechanical system and controller concurrently for a robotic flexible manipulator. There is no coupling effects among these components which exit in traditional sequential design and this concurrent development leads to the global optimal performance. A linear quadratic regulator with output feedback is used to compare the results obtained from the traditional approach and this mechatronic approach, Using the mechatronic approach, optimal beam shapes as well as the associated optimal controllers for different feedback structures and for different objective functions can be achieved. Numerical results have indicated substantial improvements on performance

Fuzzy behavior integration and action fusion for robotic excavation

This paper discusses control behavior integration and bucket action fusion for excavation control of a robotic front-end-loader type machine. To utilize the experience and expertise from skilled human operators, a fuzzy-logic based control approach is developed. A hierarchical excavation control architecture decomposes excavation goals to tasks, then tasks to behaviors, and finally behaviors to actions. The excavation actions are primitive and can be executed directly by an excavation machine. Finite state machines are used to specify the coordination and integration of behaviors for task execution and actions for behavior implementation. A simple strategy for action fusion is proposed based on fuzzy logic reasoning and the COA defuzzification method. Finally, laboratory experiments are conducted using a PUMA 560 robot arm and a Zebra force/torque sensor in a simulated rock excavation environment. Experimental results indicate that the proposed approach in this paper has led to more efficient task execution than previous approaches.

Mechatronic-based integrated construction and control of flexible manipulators

Abstract A mechatronic approach is studied here to design the mechanical system, electronical, and control components of flexible manipulators as a whole This concurrent development leads to the global optimal performance. The linear quadratic regulator with output feedback is used to compare the results obtained from the traditional approach and the mechatronic approach. A finite difference method is applied to approximate the dynamic equations. Numerical results have indicated the substantial improvements of this mechatronic method.

Robotic Excavation: Experimental Results Using Fuzzy Behavior Control

Abstract This paper presents experimental results for robotic excavation based on fuzzy behaviors. An excavation goal is achieved through excavation tasks, each erf which is completed via sequences of behaviors that are carried out by primitive actions. Both tasks and behaviors are specified by finite state machines. Behavior selection is achieved through situation assessment and behavior arbitration. A method of terminating a behavior execution is proposed. Excavation actions are specified using fuzzy logic rules acquired from human experience and heuristics. Experimental results indicate that the proposed formulation has led to a more efficient execution of excavation tasks than in a previous formulation.