In this work, we focus on improving the robot's dexterous capability by exploiting visual sensing and adaptive force control. TeachNet, a vision-based teleoperation learning framework, is exploited to map human ha...
详细信息
Path planning represents a critical research direction for dexterous arm–hand (DAH) systems. However, path planning for high-degree-of-freedom manipulators presents the following challenges: (1) time-consuming collis...
Path planning represents a critical research direction for dexterous arm–hand (DAH) systems. However, path planning for high-degree-of-freedom manipulators presents the following challenges: (1) time-consuming collision detection, and (2) an expanded search space due to high-dimensional configurations, particularly in dynamic environments. In this paper, a new path planning strategy based on rapidly-exploring random tree (RRT) path is proposed for the DAH. Firstly, an adaptive step-size RRT (ADA-RRT*) algorithm is proposed to avoid the tunneling problem caused by discrete collision detection. Secondly, to improve the efficiency of the algorithm in high-dimensional spaces, a hierarchical planning framework is first introduced, consisting of coarse planning and fine planning. Coarse planning quickly finds a rough path with large steps without considering the tunneling problem, which then guides the fine planning. Then, the beetle antennae optimization algorithm and multi-objective optimization algorithm are used to optimize the global path, reducing path length and improving path safety. Finally, the execution of corresponding simulations and experiments demonstrates the effectiveness and efficiency of the proposed method.
Object pose estimation is a core means for robots to understand and interact with their environment. For this task, monocular category-level methods are attractive as they require only a single RGB camera. However, cu...
详细信息
Assessment of myocardial viability is essential in diagnosis and treatment management of patients suffering from myocardial infarction, and classification of pathology on myocardium is the key to this assessment. This...
详细信息
As the key basis materials of Ni-MH and Ni/Cd battery electrode, the quality of the nickel foam products is closely related with the performance and safety of rechargeable batteries. In order to meet the requirements ...
详细信息
Flexibility and robustness have become key points in the development of surgical robotcontroller for physical interactions. However, the conventional impedance control schemes unaware of the actual surgical scenario,...
详细信息
ISBN:
(数字)9781728158716
ISBN:
(纸本)9781728158723
Flexibility and robustness have become key points in the development of surgical robotcontroller for physical interactions. However, the conventional impedance control schemes unaware of the actual surgical scenario, including complex physical interaction on the robot arm, lead to the loss of accuracy. In this paper, a hierarchical task impedance control scheme is proposed for Minimally Invasive Surgery (MIS) based on an operational space formulation of a 7 DoFs redundant robot. Its redundancy is exploited to guarantee a remote center of motion (RCM) constraint and to provide a flexible workspace for the medical staff to assist physicians. In addition to the achievement of the classical whole-body impedance control, the issue of uncertain disturbances will be addressed by a decoupled adaptive approximation based on a radial basis function neural network (RBFNN) within the control framework. Task performances under the hierarchical task impedance controller were validated and compared with previous work in the literature. Experimental results showed its improved performance in terms of positional error and RCM constraint, regardless of the existing uncertain physical interaction.
暂无评论