This paper describes a system for grasping known objects with unmanned aerial vehicles (UAVs) provided with dual manipulators using an RGB-D camera. Aerial manipulation remains a very challenging task. This paper cove...This paper describes a system for grasping known objects with unmanned aerial vehicles (UAVs) provided with dual manipulators using an RGB-D camera. Aerial manipulation remains a very challenging task. This paper covers three principal aspects for this task: object detection and pose estimation, grasp planning, and in-flight grasp execution. First, an artificial neural network (ANN) is used to obtain clues regarding the object’s position. Next, an alignment algorithm is used to obtain the object’s sixdimensional (6D) pose, which is filtered with an extended Kalman filter. A three-dimensional (3D) model of the object is then used to estimate an arranged list of good grasps for the aerial manipulator. The results from the detection algorithm—that is, the object’s pose—are used to update the trajectories of the arms toward the object. If the target poses are not reachable due to the UAV’s oscillations, the algorithm switches to the next feasible grasp. This paper introduces the overall methodology, and provides the experimental results of both simulation and real experiments for each module, in addition to a video showing the results.展开更多
KeJia is a domestic service robot, consisting of a mobile base, an arm, two cameras, and a set of software components for perception, manipulation, natural language understanding, motion and task planning, and decisio...KeJia is a domestic service robot, consisting of a mobile base, an arm, two cameras, and a set of software components for perception, manipulation, natural language understanding, motion and task planning, and decision making. With on-line running of these functions, a robot can adapt to dynamic environments which may have unexpected changes. In this paper, we propose a novel hierarchical method which combines motion planning with a neural network, so that the robot can tolerate errors from sensors, wear of parts, and human disturbances during motion execution. We evaluate our work on KeJia that cooks popcorn using a microwave oven, where humans try to disturb KeJia during the operation.展开更多
Locomotion and manipulation optimization is essential for the performance of tetrahedron-based mobile mechanism. Most of current optimization methods are constrained to the continuous actuated system with limited degr...Locomotion and manipulation optimization is essential for the performance of tetrahedron-based mobile mechanism. Most of current optimization methods are constrained to the continuous actuated system with limited degree of freedom(DOF), which is infeasible to the optimization of binary control multi-DOF system. A novel optimization method using for the locomotion and manipulation of an 18 DOFs tetrahedron-based mechanism called 5-TET is proposed. The optimization objective is to realize the required locomotion by executing the least number of struts.Binary control strategy is adopted, and forward kinematic and tipping dynamic analyses are performed, respectively.Based on a developed genetic algorithm(GA), the optimal number of alternative struts between two adjacent steps is obtained as 5. Finally, a potential manipulation function is proposed, and the energy consumption comparison between optimal 5-TET and the traditional wheeled robot is carried out. The presented locomotion optimization and manipulation planning enrich the research of tetrahedron-based mechanisms and provide the instruction to the successive locomotion and operation planning of multi-DOF mechanisms.展开更多
A new method based on human-likeness assessment and optimization concept to solve the problem of human-like ma- nipulation planning for articulated robot is proposed in this paper. This method intrinsically formulates...A new method based on human-likeness assessment and optimization concept to solve the problem of human-like ma- nipulation planning for articulated robot is proposed in this paper. This method intrinsically formulates the problem as a con- strained optimization problem in robot configuration space. The robot configuration space is divided into different subregions by human likeness assessment. A widely used strategy, Rapid Upper Limb Assessment （RULA） in applied ergonomics, is adopted here to evaluate the human likeness of robot configuration. A task compatibility measurement of the robot velocity transmission ratio along a specified direction is used as the target function for the optimization problem. Simple illustrative examples of this method applied to a two Degree of Freedom （DOF） planar robot that resembles the upper limb of a human are presented. Further applications to a humanoid industrial robot SDA10D are also presented. The reasonable planning results for these applications assert the effectiveness of our method.展开更多
Better flexibility and controllability have been introduced into distribution system with the development of new loads and resources.As a consequence,the connotations and tools for evaluating the planning solution nee...Better flexibility and controllability have been introduced into distribution system with the development of new loads and resources.As a consequence,the connotations and tools for evaluating the planning solution need to be further enriched.This paper proposes a fast algorithm to quantify steady-state voltages and load profiles in distribution system by simulating the manipulation control process of controllable resources,taking the efficiency and ease of use into account.In this method,a complex distribution system is decoupled into several simple parts according to the ports of the DC interlink.Then,to achieve the qualified voltages and load profiles,the manipulation details of controllable resources are simulated following a certain control sequence in each part.Finally,the analysis results of each part are matched and filtered to obtain a complete evaluation.Five types of the most commonly controllable resources are considered in this method.The effectiveness of the proposed method is demonstrated through a case study based on field data from an actual distribution system.展开更多
文摘This paper describes a system for grasping known objects with unmanned aerial vehicles (UAVs) provided with dual manipulators using an RGB-D camera. Aerial manipulation remains a very challenging task. This paper covers three principal aspects for this task: object detection and pose estimation, grasp planning, and in-flight grasp execution. First, an artificial neural network (ANN) is used to obtain clues regarding the object’s position. Next, an alignment algorithm is used to obtain the object’s sixdimensional (6D) pose, which is filtered with an extended Kalman filter. A three-dimensional (3D) model of the object is then used to estimate an arranged list of good grasps for the aerial manipulator. The results from the detection algorithm—that is, the object’s pose—are used to update the trajectories of the arms toward the object. If the target poses are not reachable due to the UAV’s oscillations, the algorithm switches to the next feasible grasp. This paper introduces the overall methodology, and provides the experimental results of both simulation and real experiments for each module, in addition to a video showing the results.
基金Project supported by the National Natural Science Foundation of China(Nos.U1613216 and 61573333)the Fundamental Research Funds for the Central Universities,China
文摘KeJia is a domestic service robot, consisting of a mobile base, an arm, two cameras, and a set of software components for perception, manipulation, natural language understanding, motion and task planning, and decision making. With on-line running of these functions, a robot can adapt to dynamic environments which may have unexpected changes. In this paper, we propose a novel hierarchical method which combines motion planning with a neural network, so that the robot can tolerate errors from sensors, wear of parts, and human disturbances during motion execution. We evaluate our work on KeJia that cooks popcorn using a microwave oven, where humans try to disturb KeJia during the operation.
基金Supported by National Science-Technology Support Plan Projects of China (Grant No.2015BAK04B00)2015 Sino-German Postdoc Scholarship Program (Grant No.57165010)
文摘Locomotion and manipulation optimization is essential for the performance of tetrahedron-based mobile mechanism. Most of current optimization methods are constrained to the continuous actuated system with limited degree of freedom(DOF), which is infeasible to the optimization of binary control multi-DOF system. A novel optimization method using for the locomotion and manipulation of an 18 DOFs tetrahedron-based mechanism called 5-TET is proposed. The optimization objective is to realize the required locomotion by executing the least number of struts.Binary control strategy is adopted, and forward kinematic and tipping dynamic analyses are performed, respectively.Based on a developed genetic algorithm(GA), the optimal number of alternative struts between two adjacent steps is obtained as 5. Finally, a potential manipulation function is proposed, and the energy consumption comparison between optimal 5-TET and the traditional wheeled robot is carried out. The presented locomotion optimization and manipulation planning enrich the research of tetrahedron-based mechanisms and provide the instruction to the successive locomotion and operation planning of multi-DOF mechanisms.
基金The National Natural Science Foundation of China，National High Technology Research and Development Program of China，The Research Innovation Program for College Graduates of Jiangsu Province，The Excellent Doctoral Dissertation Foundation of Southeast University
文摘A new method based on human-likeness assessment and optimization concept to solve the problem of human-like ma- nipulation planning for articulated robot is proposed in this paper. This method intrinsically formulates the problem as a con- strained optimization problem in robot configuration space. The robot configuration space is divided into different subregions by human likeness assessment. A widely used strategy, Rapid Upper Limb Assessment （RULA） in applied ergonomics, is adopted here to evaluate the human likeness of robot configuration. A task compatibility measurement of the robot velocity transmission ratio along a specified direction is used as the target function for the optimization problem. Simple illustrative examples of this method applied to a two Degree of Freedom （DOF） planar robot that resembles the upper limb of a human are presented. Further applications to a humanoid industrial robot SDA10D are also presented. The reasonable planning results for these applications assert the effectiveness of our method.
基金supported by National Key Research and Development Program(No.2017YFB0903300)National Natural Science Foundation of China(No.51777105).
文摘Better flexibility and controllability have been introduced into distribution system with the development of new loads and resources.As a consequence,the connotations and tools for evaluating the planning solution need to be further enriched.This paper proposes a fast algorithm to quantify steady-state voltages and load profiles in distribution system by simulating the manipulation control process of controllable resources,taking the efficiency and ease of use into account.In this method,a complex distribution system is decoupled into several simple parts according to the ports of the DC interlink.Then,to achieve the qualified voltages and load profiles,the manipulation details of controllable resources are simulated following a certain control sequence in each part.Finally,the analysis results of each part are matched and filtered to obtain a complete evaluation.Five types of the most commonly controllable resources are considered in this method.The effectiveness of the proposed method is demonstrated through a case study based on field data from an actual distribution system.
