Search results

Installing a tight tolerant stepped shaft is not a trivial task for an industrial robot. If all peg-hole constraints are complete, the cascaded peg-in-hole task can be simplified into several independent stages and accomplished one by one. However, if some of the constraints are incomplete, the cross stage interference will bring additional difficulties. This paper aims to discuss the cascaded peg-in-hole problem with incomplete constraints.

In this paper, the problem is formulated according to geometric parameters of the stepped shaft and completeness of the corresponding hole. The possible jamming type is modeled and analyzed. A contact modeling and control strategy is proposed to compensate the peg postures under incomplete constraints.

The above methods are implemented on an experiment platform and the results verify the effectiveness of the proposed robotic assembly strategy.

Based on force/torque sensor, a hybrid control strategy for incomplete constraints cascaded peg-in-hole assembly problem is proposed.

The purpose of this paper is to estimate the contact-consistent object poses during contact-rich manipulation tasks based only on visual sensors.

The method follows a four-step procedure. Initially, the raw object poses are retrieved using the available object pose estimation method and filtered using Kalman filter with nominal model; second, a group of particles are randomly generated for each pose and evaluated the corresponding object contact state using the contact simulation software. A probability guided particle averaging method is proposed to balance the accuracy and safety issues; third, the independently estimated contact states are fused in a hidden Markov model to remove the abnormal contact state observations; finally, the object poses are refined by averaging the contact state consistent particles.

The experiments are performed to evaluate the effectiveness of the proposed methods. The results show that the method can achieve smooth and accurate pose estimation results and the estimated contact states are consistent with ground truth.

This paper proposes a method to obtain contact-consistent poses and contact states of objects using only visual sensors. The method tries to recover the true contact state from inaccurate visual information by fusing contact simulations results and contact consistency assumptions. The method can be used to extract pose and contact information from object manipulation tasks by just observing the demonstration, which can provide a new way for the robot to learn complex manipulation tasks.

Delta robot is a parallel robot specifically designed for high-speed pick and place tasks. However, sometimes they are asked to perform additional assembling and squeezing actions, which is beyond the capability of position-controlled Delta robots. Force sensors may be expensive and add mass to the system. Therefore, the purpose of this paper is to study sensorless force control of Delta robots using limited access interface.

Static force analysis is performed to establish a relation between joint torques and external forces. The joint torques are observed from signals provided by motor drivers. A distributed mass model is proposed to compensate the gravity of upper arms and forearms. To minimize the effect of backlash and nonlinear frictions brought by gearboxes, model parameters are calibrated in two separated modes: “LIFTING” and “LOWERING”. Finally, a hybrid force estimation model is built to deal with both cases simultaneously. Surrogate model-based force control law is proposed to increase the force control loop rate and handle the force control problem for discrete position-controlled Delta robots.

The results show that the force estimation model is effective and mode separation can significantly improve the accuracy. The force control laws indeed stabilize the robot in desired states.

The proposed solution is based on position-controlled commercial Delta robot and requires no additional force sensor. It is able to extend Delta robots’ capability and meet requirements of emerging complex tasks.

The purpose of this paper is to design a multifingered dexterous hand grasping planning method that can efficiently perform grasping tasks on multiple dexterous hand platforms.

The grasping process is divided into two stages: offline and online. In the offline stage, the grasping solution form is improved based on the forward kinematic model of the dexterous hand. A comprehensive evaluation method of grasping quality is designed to obtain the optimal grasping solution offline data set. In the online stage, a safe and efficient selection strategy of the optimal grasping solution is proposed, which can quickly obtain the optimal grasping solution without collision.

The experiments verified that the method can be applied to different multifingered dexterous hands, and the average grasping success rate for objects with different structures is 91.7%, indicating a good grasping effect.

Using a forward kinematic model to generate initial grasping points can improve the generality of grasping planning methods and the quality of initial grasping solutions. The offline data set of optimized grasping solutions can be generated faster by the comprehensive evaluation method of grasping quality. Through the simple and fast obstacle avoidance strategy, the safe optimal grasping solution can be quickly obtained when performing a grasping task. The proposed method can be applied to automatic assembly scenarios where the end effector is a multifingered dexterous hand, which provides a technical solution for the promotion of multifingered dexterous hands in industrial scenarios.

Learning from demonstration (LfD) provides an intuitive way for non-expert persons to teach robots new skills. However, the learned motion is typically fixed for a given scenario, which brings serious adaptiveness problem for robots operating in the unstructured environment, such as avoiding an obstacle which is not presented during original demonstrations. Therefore, the robot should be able to learn and execute new behaviors to accommodate the changing environment. To achieve this goal, this paper aims to propose an improved LfD method which is enhanced by an adaptive motion planning technique.

The LfD is based on GMM/GMR method, which can transform original off-line demonstrations into a compressed probabilistic model and recover robot motion based on the distributions. The central idea of this paper is to reshape the probabilistic model according to on-line observation, which is realized by the process of re-sampling, data partition, data reorganization and motion re-planning. The re-planned motions are not unique. A criterion is proposed to evaluate the fitness of each motion and optimize among the candidates.

The proposed method is implemented in a robotic rope disentangling task. The results show that the robot is able to complete its task while avoiding randomly distributed obstacles and thereby verify the effectiveness of the proposed method. The main contributions of the proposed method are avoiding unforeseen obstacles in the unstructured environment and maintaining crucial aspects of the motion which guarantee to accomplish a skill/task successfully.

Traditional methods are intrinsically based on motion planning technique and treat the off-line training data as a priori probability. The paper proposes a novel data-driven solution to achieve motion planning for LfD. When the environment changes, the off-line training data are revised according to external constraints and reorganized to generate new motion. Compared to traditional methods, the novel data-driven solution is concise and efficient.

The electronics industries are relying increasingly on robotics for their production. Wafer handling robots are used to transfer wafers between wafer processing stations. A pick‐measure‐place method is typically utilized to transfer wafers accurately. The measurement step is performed using an aligner, which is time‐consuming. To increase wafer transfer efficiency, it is desirable to speed up the measurement process or place it in parallel with other operations. To solve the problem, optic sensors are installed at each station to estimate the wafer eccentricity on‐the‐fly. The eccentricity values are then applied to control the robot to place the wafer directly onto another station accurately without using the aligner. However, current methods face problems to achieve high accuracy requirements to meet the electronic manufacturing needs. The purpose of this paper is to develop a technique to improve the wafer handling performance in semiconductor manufacturing.

The kinematics model of the wafer handling robot is developed. Two sensor location calibration algorithms are proposed. Method I is based on the wafer handling path. Method II uses the offset paths from the wafer handling path. The results from these two methods are compared. To compute the wafer eccentricity on‐the‐fly, a wafer eccentricity estimation technique is developed.

The developed methods are implemented using a wafer handling robotic system in semiconductor manufacturing. The wafer eccentricity estimation errors are greatly reduced using the developed methods. The experimental results demonstrate that Method II achieves better results and can be used to improve the wafer handling accuracy and efficiency.

The proposed technique is implemented and tested many times on a wafer handing robotic system. The notch alignment in the wafer handling needs further research.

The developed method is validated using a system in semiconductor manufacturing. Hence the developed method can be directly implemented in production if the notch of a wafer can be identified.

This paper provides techniques to improve the wafer handling accuracy in semiconductor manufacturing. Compared with the results using other methods, Method II greatly increases the wafer handling accuracy to satisfy the semiconductor manufacturing needs.

The purpose of this study is to address a significant gap in the understanding of entrepreneurship at the microfoundation level. It focuses on how individual entrepreneurs, specifically Hongbang entrepreneurs in China from 1896 to 1949, shape and transform their contexts. The aim is to provide a deeper understanding of the mechanisms that facilitate entrepreneurial success.

The study adopts a microhistorical approach, investigating the case of Hongbang entrepreneurs in China during 1896-1949. It involves an in-depth examination of historical records to explore the strategic interactions between these entrepreneurs and core stakeholders such as consumers, financial intermediaries, government regulators, and human resources. The research methodology emphasizes a process-oriented view, examining the evolution of personalized networks into extensive connections.

The research reveals that Hongbang entrepreneurs successfully reshaped their unfavorable embedded contexts by strategically collaborating with key stakeholders. They influenced consumer tastes, allied with financial intermediaries, negotiated with governments on regulation policies, and developed human resource stocks. The transformation was facilitated by the evolution of their networks from personalized to extensive connections. These findings highlight the localized strategies such as cronyism in resource acquisition within China’s private property development industry.

This study contributes to the field by offering insights into entrepreneurial contextualization and networking. It sheds light on the complex interplay between entrepreneurs and their contexts, providing a nuanced understanding of localized strategies in the Chinese context. The findings add value to the discourse on entrepreneurship by elucidating the strategic and processual acts through which entrepreneurs engage with stakeholders and reshape their environments.