Wing Kwong Chung

A realtime hand gesture recognition based on Haar wavelet representation

Nowadays, sign language is commonly used as a communication language for auditory handicapped people. In addition to voice and controller pads, hand gestures can also be an effective way of communication between humans and robots or even between auditory handicapped people and robots. To be an effective sign recognition system, it should be glove-free, fast, small database and accurate. In this project, we aim to propose a hand gesture recognition system which performs realtime recognition. We reduce the database size by standardizing the orientation of hands using the idea of principal axis. To facilitate the matching process, we propose a codeword scheme based on the features of hand gestures. We also propose the use of a new measurement metric with a penalty score which enhances the recognition accuracy. Experimental results have proved the success of the proposed hand gesture recognition system in terms of time, database size, and accuracy.

A generalized 3-D path planning method for robots using Genetic Algorithm with an adaptive evolution process

Traditionally, path planning for robots is modeled as optimization problems. One of the most commonly used optimization strategies is Genetic Algorithm (GA) since it always guarantees a nearly shortest path even a global path can not be obtained within a reasonable time. In fact, the performance enhancement of GA is still an open topic for researchers by designing different genetic operators. In addition to this, we propose a new criterion for the selection of genetic operators during evolution in order to further facilitate the searching efficiency. In this paper, we propose a generalized 3-D path planning method for robots using GA with an adaptive evolution process. Based on the framework of traditional GA, we first introduce a new genetic operator, called Bind-NN which randomly divides and recombines an elitist chromosome based on nearest neighbor. We also show that by choosing the fitness variance of the shortest path in last generations as a guidance in selecting genetic operators during evolution, the search efficiency can be significantly improved, thus proposing a genetic operators selection scheme. In the latter part of this paper, we present the algorithm evaluation by stimulating a sample path planning problem on a structural frame. With the use of the proposed genetic operator and selection scheme, experimental results show a significant improvement in terms of search effectiveness and efficiency.

A novel design of Movable Gripper for non-enclosable truss climbing

In this paper, we present a novel Movable Gripper (MovGrip) which targets on climbing non-enclosable rectangular trusses such as bridges and space stations. It is designed with a transformation mechanism which provides the features of parallel grippers, rotatory grippers, and active wheels. For truss climbing, MovGrip acts as a parallel gripper which allows the change in gripping width according to different size of trusses. Since MovGrip is equipped with active wheels, fast climbing motion can therefore be realized. Moreover, MovGrip can be transformed into a mobile platform which is suitable for the navigation on ground. It weighs only 500 grams with a climbing speed of 3 cm/s. To maintain the climbing stability, we steer the rotation axis of wheels. By this, a directional pulling force (from MovGrip to truss surface) can be distributed from the drive force of wheels which pulls MovGrip towards the truss while climbing. Experimental results show that tilting of MovGrip can be auto-adjusted based on the proposed design. Also, it is shown that the load carrying capability of MovGrip is approximately 1 kg which is 2 times of its weight.

A real-time vehicle safety system

With the increase of vehicle amount all over the world, vehicle safety has become a tremendous problem. Chained accidents, which result in numerous losses of lives and properties, happen due to the fact that the following drivers are unaware of the accident occurrence. In this paper, a real-time vehicle safety system is proposed. A prototype test platform, consisting of collision detection and classification module, vehicle-to-vehicle (V2V) communication module and graphic user interface (GUI) module, has been built for validating the performance. 12 sensors are installed in collision detection module. Threshold under rule based strategy is adopted for collision classification. We also propose a GPS based AODV (GBAODV) protocol for V2V communication application. One full version and eight sets of portable version subsystems are implemented for road test. The experiment results validate the performance of this safety vehicle system.

A Parallel-Structure Solder Paste Inspection System

In this paper, we present an innovative design of a solder paste inspection system that can be practically integrated into existing solder paste printing machines. Since solder paste inspection systems usually occupy a large vertical space, we designed a mirror box that can redirect the transmission of fringe patterns. In this way, a new parallel-structure solder paste inspection system with a significant reduction in the vertical constraint is developed. We also developed a hybrid weighting algorithm that applies the distance and fringe contrast to acquire the height of solder pastes. Furthermore, we developed an algorithm that generates the 2-D image from the fringe pattern images during the four-step algorithm. It reduces the time required for solder paste inspection compared to traditional approaches that use special lighting systems to create the 2-D image. Based on the results of the height acquisition algorithm, 2-D and 3-D solder paste inspections are performed. Experimental results show that our system can inspect a 20 mm times 20 mm printed circuit board area within 2 s to detect common 2-D and 3-D defects, and the maximum standard deviation for the average height is 3 mum.

Novel Design of Gaits on Space Station for Dynamic Disturbance Minimization

In this paper, we propose a novel design of gaits for space manipulators so as to minimize the dynamic disturbance on a space station. Without modifying their joint configuration, we first propose the use of our previous developed gripping methodology. It combines the concepts of wheels motion in parallel grippers to reduce the swing motions in conventional gaits. For the proposed gaits, three major aspects are considered including 1) linear motion; 2) turning; and 3) exterior transition. Based on the conventional modeling approach for fixed base space manipulators, we extend the method to formulate the dynamic coupling during wheels motion. It is to visualize the manipulator as a prismatic joint with its gripping base moving with wheels motion. Also, we develop an experimental platform for verification. For disturbance analysis, various simulations have been conducted. Results have validated that the proposed gaits generate the lowest disturbance on a space station.

A novel frame climbing robot: Frambot

In this paper, we present a novel frame climbing robot, called Frambot which aims to climb on non-enclosable rectangular trusses. Frambot weighs only 1.6kg and consists of two grippers connected by a body linkage. For the grippers of Frambot, it provides not only the grasp on a truss structure, but also allows a linear truss climbing motion. Based on the mobility of Frambot, we propose new climbing gaits which aim to enhance the stability of truss climbing by reducing the extra angular moment generated during the swing motions in traditional truss climbing gaits. Both motion and dynamic torque simulations are performed for the analysis of the proposed gaits. Finally, the proposed gaits are realized in our robot prototype. Experimental results show that Frambot is capable in climbing non-enclosable trusses with the new climbing gaits.

Path planning algorithm for space manipulator with a minimum energy demand

This paper presents a methodology to plan a global path for the gaits of space manipulators with a minimum total energy demand. Different from conventional approaches, we propose the consideration of the motions composition for a manipulator to plan a path. For the path planning problem, it is first modeled as a Traveling Salesman Problem (TSP) and the optimization goal is to search a path with a minimum energy demand. After that, the individual energy demand of different gaits of a space manipulator is estimated and analyzed. To solve the optimization problem, conventional genetic algorithm (GA) is utilized. To enhance the performance of GA, we design and develop a novel genetic operator, called Planar-NN. It aims to search a solution path with more motion primitives which contribute a lower energy demand. To evaluate the performance of the proposed algorithm, numerous simulations are performed. Results show that it can search a path with the lowest total energy demand.

Optimized methodologies for augmented reality markers based localization

Localization is one of the key research topics in robotics. Although computer vision based methodologies such as Augmented Markers provides a realtime localization approach, the sensing range and localization accuracy are the main limitations for applications. In this paper, we proposed the use of a problem solving tool, TRIZ to overcome these limitations. Among the tools provided by TRIZ, we illustrated the selection of principles for problem solving. To enhance the sensing range, a novel AR marker is presented. To improve the localization accuracy, we presented the use of an AR polyhedron for system localization. With the use of an AR cube for illustration, we further developed a new optimization strategy. It is a weighted sum method which aims to optimize the position of the AR cube by considering the orientation of different AR markers captured by a camera. To evaluate the proposed methods, different experiments have been conducted including static and dynamic localizations. Results show that the proposed solutions and strategy can significantly improve the sensing range and accuracy of the conventional AR localization system.

System and design of a compact and heavy-payload AGV system for flexible production line

This paper presents a new Automatic Guided Vehicle (AGV) system, in which unique compact and heavy-payload under-cart design, high precision hybrid-mode stopping, modularized software and distributed AGV-caller system, are integrated to provide a reliable and worker-friendly AGV system for the flexible production Une. Besides, the results of a series of in-field tests validate the payload and precise stopping performance of our AGV system.