Search results

The purpose of this study is realizing human-like motions and performance through musculoskeletal robots and brain-inspired controllers. Human-inspired robotic systems, owing to their potential advantages in terms of flexibility, robustness and generality, have been widely recognized as a promising direction of next-generation robots.

In this paper, a deep forward neural network (DFNN) controller was proposed inspired by the neural mechanisms of equilibrium-point hypothesis (EPH) and musculoskeletal dynamics.

First, the neural mechanism of EPH in human was analyzed, providing the basis for the control scheme of the proposed method. Second, the effectiveness of proposed method was verified by demonstrating that equilibrium states can be reached under the constant activation signals. Finally, the performance was quantified according to the experimental results.

Based on the neural mechanism of EPH, a DFNN was crafted to simulate the process of activation signal generation in human motion control. Subsequently, a bio-inspired musculoskeletal robotic system was designed, and the high-precision target-reaching tasks were realized in human manner. The proposed methods provide a direction to realize the human-like motion in musculoskeletal robots.

The purpose of this paper is to develop a dual peg-in-hole insertion strategy. Dual peg-in-hole insertion is the most common task in manufacturing. Most of the previous work develop the insertion strategy in a two- or three-dimensional space, in which they suppose the initial yaw angle is zero and only concern the roll and pitch angles. However, in some case, the yaw angle could not be ignored due to the pose uncertainty of the peg on the gripper. Therefore, there is a need to design the insertion strategy in a higher-dimensional configuration space.

In this paper, the authors handle the insertion problem by converting it into several sub-problems based on the attractive region formed by the constraints. The existence of the attractive region in the high-dimensional configuration space is first discussed. Then, the construction of the high-dimensional attractive region with its sub-attractive region in the low-dimensional space is proposed. Therefore, the robotic insertion strategy can be designed in the subspace to eliminate some uncertainties between the dual pegs and dual holes.

Dual peg-in-hole insertion is realized without using of force sensors. The proposed strategy is also used to demonstrate the precision dual peg-in-hole insertion, where the clearance between the dual-peg and dual-hole is about 0.02 mm.

The sensor-less insertion strategy will not increase the cost of the assembly system and also can be used in the dual peg-in-hole insertion.

The theoretical and experimental analyses for dual peg-in-hole insertion are proposed without using of force sensor.

The purpose of this paper is to solve the non-fragile consensus problem of networked robotic manipulators over communication networks by using information from topology-dependent memory.

This paper proposes a topology-dependent memory protocol with distributed consensus controllers for multiple networked robotic manipulators.

The distributed controller gain fluctuations are taken into account with sampled data information exchanges. By the derived results of model transformation, the topology-dependent memory protocol is investigated using sufficient consensus criteria in the form of linear matrix inequalities.

A novel consensus protocol with topology-dependent memory is designed, which can potentially improve consensus performance and deal with the controller gain fluctuations of the robotic manipulators in practical applications.

Limited by the types of sensors, the state information available for musculoskeletal robots with highly redundant, nonlinear muscles is often incomplete, which makes the control face a bottleneck problem. The aim of this paper is to design a method to improve the motion performance of musculoskeletal robots in partially observable scenarios, and to leverage the ontology knowledge to enhance the algorithm’s adaptability to musculoskeletal robots that have undergone changes.

A memory and attention-based reinforcement learning method is proposed for musculoskeletal robots with prior knowledge of muscle synergies. First, to deal with partially observed states available to musculoskeletal robots, a memory and attention-based network architecture is proposed for inferring more sufficient and intrinsic states. Second, inspired by muscle synergy hypothesis in neuroscience, prior knowledge of a musculoskeletal robot’s muscle synergies is embedded in network structure and reward shaping.

Based on systematic validation, it is found that the proposed method demonstrates superiority over the traditional twin delayed deep deterministic policy gradients (TD3) algorithm. A musculoskeletal robot with highly redundant, nonlinear muscles is adopted to implement goal-directed tasks. In the case of 21-dimensional states, the learning efficiency and accuracy are significantly improved compared with the traditional TD3 algorithm; in the case of 13-dimensional states without velocities and information from the end effector, the traditional TD3 is unable to complete the reaching tasks, while the proposed method breaks through this bottleneck problem.

In this paper, a novel memory and attention-based reinforcement learning method with prior knowledge of muscle synergies is proposed for musculoskeletal robots to deal with partially observable scenarios. Compared with the existing methods, the proposed method effectively improves the performance. Furthermore, this paper promotes the fusion of neuroscience and robotics.

The purpose of this paper is to give a novel sensor‐less manipulation strategy for the high‐precision assembly of an eccentric peg into a hole.

Based on the authors' previous work on the attractive region, this paper proposes the sensorless eccentric peg‐hole insertion strategy. The analysis is based on the visible strategic behaviors by decomposing the high‐dimensional configuration space of the eccentric peg‐hole into two low dimensional configuration subspaces. Then, the robotic manipulations can be designed in the configuration subspaces. Finally, a typical industry application, fitting an eccentric crankshaft into a bearing hole of the automotive air‐conditioners, is used to validate the presented strategy.

The attractive region constructed in the configuration space has been applied to guide the robotic manipulations, such as, the locating and the insertion.

The designed robotic assembly system without using force sensor or flexible wrist has an advantage in terms of expense and durability for the automotive air‐conditioners manufacturing industry.

Most previous work on sensorless manipulation strategy has concentrated on inserting a symmetric peg into a hole. However, for the assembly of an eccentric peg into a hole, the robotic manipulations should be explored in a high‐dimensional configuration space as the six‐DOFs of the eccentric peg. In this paper, the decomposition method of the high‐dimensional configuration space would make the system analysis visible; then, the assembly strategy can be easily designed in the two subspaces.

China represents around 20% of the world's population, and her economy is still performing well under economic crisis. Historical events have shaped different parts of China with different economic developments and cultural encounters. The most prominent difference is between Hong Kong and the Mainland. This chapter would like to examine the development and issues of fashion retailing in China. For better understanding, this chapter starts with a brief discussion on apparel industry development and fashion culture in Hong Kong and the Mainland, follows by historical development and then presents systems of fashion retailing in both Hong Kong and the Mainland. Desktop research and exploratory research techniques were employed. Stores of international fashion luxury brands in Hong Kong, Shanghai and Beijing were visited. Comparison of branding issues, particularly for luxury market in Hong Kong and the Mainland are discussed, so are future directions of fashion retailing in these places.

The purpose of this paper is to introduce the physical structure and the control mechanism of human motor nervous system to the robotic system in a tentative manner to improve the compliance/flexibility/versatility of the robot.

A brief review is focused on the concept of compliance, the compliance-based methods and the application of some compliance-based devices. Combined with the research on the physical structure and the control mechanism of human motor nervous system, a new drive structure and control method is proposed.

Introducing the physical structure and the control mechanism of human motor nervous system can improve the compliance/flexibility/versatility of the robot, without bringing in more complexity or inefficiency to the system, which helps in the assembly automation tasks.

The proposed drive structure and control method are useful to build up a novel, low-cost robotic assembly automation system, which is easy to interact and cooperate with humans.

The aim of this paper was to investigate the passive corrosion control and active corrosion protective effect of the reinforced concrete structures by electrochemical chloride removal (ECR) method and inhibitors approach, respectively.

The concentration of aggressive chloride ion distributed from the reinforcing steel to the surface of the concrete cover was analyzed during the ECR processes. Besides, the half-cell potential, the concrete resistance R _c , the polarization resistance R _p and the capacitance of double layer C _dl of the steel/concrete system were used to characterize the electrochemical performance of the concrete prisms.

The effectiveness of ECR could be enhanced by increasing the amplitude of potential or prolonging the time. Inhibitor SBT-ZX(I) could successfully prevent the corrosion development of the reinforcing steel in concrete.

The research provides the scientific basis for the practical application of ECR and inhibitors in the field.

Picking up pistons in arbitrary poses is an important step on car engine assembly line. The authors usually use vision system to estimate the pose of the pistons and then guide a stable grasp. However, a piston in some poses, e.g. the mouth of the piston faces forward, is hardly to be directly grasped by the gripper. Thus, we need to reorient the piston to achieve a desired pose, i.e. let its mouth face upward, for grasping.

This paper aims to present a vision-based picking system that can grasp pistons in arbitrary poses. The whole picking process is divided into two stages. At localization stage, a hierarchical approach is proposed to estimate the piston’s pose from image which usually involves both heavy noise and edge distortions. At grasping stage, multi-step robotic manipulations are designed to enable the piston to follow a nominal trajectory to reach to the minimum of the distance between the piston’s center and the support plane. That is, under the design input, the piston would be pushed to achieve a desired orientation.

A target piston in arbitrary poses would be picked from the conveyor belt by the gripper with the proposed method.

The designed robotic bin-picking system using vision is an advantage in terms of flexibility in automobile manufacturing industry.

The authors develop a methodology that uses a pneumatic gripper and 2D vision information for picking up multiple pistons in arbitrary poses. The rough pose of the parts are detected based on a hierarchical approach for detection of multiple ellipses in the environment that usually involve edge distortions. The pose uncertainties of the piston are eliminated by multi-step robotic manipulations.