Kinesthetic teaching is an established method of teaching robots new skills without requiring robotics or programming knowledge. However, the inertia and uncoordinated motions of individual joints decrease the intuiti...
详细信息
ISBN:
(纸本)9781467383707
Kinesthetic teaching is an established method of teaching robots new skills without requiring robotics or programming knowledge. However, the inertia and uncoordinated motions of individual joints decrease the intuitiveness and naturalness of interaction and impair the quality of the learned skill. this paper proposes a method to ease kinesthetic teaching by combining the idea of incremental learning through warping several demonstrations into a common frame with virtual tool dynamics to assist the user during teaching. In fact, during a sequence of demonstrations the stiffness of the robot under Cartesian impedance control is gradually increased, to provide stronger assistance to the user based on the demonstrations accumulated up to that moment. therefore, the operator has the opportunity to progressively refine the task's model while the robot more docilely follows the learned action. Robot experiments and a user study performed on 25 novice users show that the proposed approach improves both usability as well as resulting skill quality.
Many research works have been reported with respect to the relation between neural and fuzzy systems. Looking for a synergistic relation of these technologies, an important property of neural network-based systems is ...
详细信息
Many research works have been reported with respect to the relation between neural and fuzzy systems. Looking for a synergistic relation of these technologies, an important property of neural network-based systems is their learning capacity, that permits to embed self-organization in fuzzy logic systems. In this paper, a new neuro-fuzzy system, called FasBack, is proposed, that combines learning based on prediction error minimization and pattern matching. FasBack adds error-based learning to a previously proposed model, called FasArt, which extended and formalized neural networks models of the ART family, as fuzzy logic systems. Experimental results are presented in nonlinear systems identification problems, typically used in the literature.
Semantic mapping has many use cases in mobile robotics. For example, in logistic environments, it is applied to find and transport loading goods or in mobile manipulation to identify objects to grasp, and it often rel...
详细信息
ISBN:
(数字)9798331518158
ISBN:
(纸本)9798331518165
Semantic mapping has many use cases in mobile robotics. For example, in logistic environments, it is applied to find and transport loading goods or in mobile manipulation to identify objects to grasp, and it often relies on neural networks to accomplish image detection and segmentation for semantic mapping. Data sets are usually required to train those neural networks, which are difficult to generate for many organizations since their creation requires qualified personnel. this paper demonstrates how federated learning, combined with supervised neural networks, effectively reduces the effort for semantic map training while maintaining data sovereignty. It allows organizations to facilitate their individual training data generation efforts to build semantic maps by collaborating with other organizations without sharing their training data and, therefore, not losing their data sovereignty. At the same time, they can reduce their individual effort to generate and train data.
this paper describes the use of genetic algorithms (GAs) for optimizing the parameters of PID controllers for a 6-DOF robot arm. An efficient GA is designed to optimal-tune the parameters of the PID controller of each...
详细信息
this paper describes the use of genetic algorithms (GAs) for optimizing the parameters of PID controllers for a 6-DOF robot arm. An efficient GA is designed to optimal-tune the parameters of the PID controller of each joint for a single step response and for the tracking of other specified trajectories. this GA is required to optimize fitness functions related to the combinations of different performance indices such as ISE, time-optimal and others. the simulations are carried out on a PUMA 560 arm model being controlled by PID controllers withtheir parameters optimized using the proposed GA. the simulation results obtained are compared withthat obtained by traditional optimization techniques, wherever applicable.< >
Reinforcement Learning (RL) is a branch of machine learning applied to many applications, such as mechatronics and robotics. RL allows more challenges to be resolved in robotics due to the high capacity for problem de...
详细信息
Autonomous docking for underwater drones is crucial for various marine applications. this paper introduces an approach to autonomous underwater vehicle (AUV) docking using ArUco marker-based localization, as demonstra...
详细信息
ISBN:
(数字)9798331520038
ISBN:
(纸本)9798331520045
Autonomous docking for underwater drones is crucial for various marine applications. this paper introduces an approach to autonomous underwater vehicle (AUV) docking using ArUco marker-based localization, as demonstrated by Project MIRA, at the Tau Autonomy Center, Norway. the method combines a control system with dual-feed computer vision based perception to achieve autonomy. the control system is based on a cascaded PID controller fine-tuned using various external sensors and optimization techniques. the vision system utilizes ArUco markers for 3D positioning. Our method uses visual markers to help the drone navigate to a custom docking pad. We achieved stable and reliable docking by combining advanced control systems using visual-inertial sensors. this work highlights the potential of using visual markers and smart control systems for underwater drone operations.
this paper mainly introduces the research of quadrotor UAV in mobile target detection tracking and redetection, and proposes KCF-Y algorithm and KCF-Ys algorithm. KCF- Y algorithm combines Kernelized Correlation Filte...
详细信息
ISBN:
(数字)9798350353594
ISBN:
(纸本)9798350353600
this paper mainly introduces the research of quadrotor UAV in mobile target detection tracking and redetection, and proposes KCF-Y algorithm and KCF-Ys algorithm. KCF- Y algorithm combines Kernelized Correlation Filters (KCF) algorithm and YOLO algorithm, which solves some limitations of KCF algorithm in target tracking, and improves the accuracy and robustness of the algorithm for moving target tracking. the KCF-Ys algorithm uses the YOLOv8 ONNX model to realize the target center control and improve the real-time tracking of the mobile target. Finally, the superiority of the proposed algorithm and the effectiveness of the UAV tracking system.
Text-to-SQL is a technology that converts natural language queries into the structured query language SQL. A novel research approach that has recently gained attention focuses on methods based on the complexity of SQL...
详细信息
ISBN:
(数字)9798350353594
ISBN:
(纸本)9798350353600
Text-to-SQL is a technology that converts natural language queries into the structured query language SQL. A novel research approach that has recently gained attention focuses on methods based on the complexity of SQL queries, achieving notable performance improvements. However, existing methods entail significant storage and training costs, which hampers their practical application. To address this issue, this paper introduces a method for Text-to-SQL based on Refined Schema and Hardness Prompt. By filtering out low-relevance schema information with a refined schema and identifying query hardness through a Language Model (LM) to form prompts, this method reduces storage and training costs while maintaining performance. It's worth mentioning that this method is applicable to any sequence-to-sequence (seq2seq) LM. Our experiments on the Spider dataset, specifically with large-scale LMs, achieved an exceptional Execution accuracy (EX) of 82.6%, demonstrating the effectiveness and greater suitability of our method for real-world applications.
To address the problem of residual vibration caused by system flexibility after a high-speed motion stop of a multi-axis servo system, a post-adaptive input shaping method is proposed, which does not require parameter...
详细信息
ISBN:
(数字)9798350307535
ISBN:
(纸本)9798350307542
To address the problem of residual vibration caused by system flexibility after a high-speed motion stop of a multi-axis servo system, a post-adaptive input shaping method is proposed, which does not require parameter identification of the system and tracks the optimal parameter vectors of the input shaper well in a non-stationary environment. the method is based on the recursive least squares method and takes advantage of the fact that the inverse matrix of the correlation matrix is a symmetric matrix to reduce the computational effort of the RLS algorithm. In order to solve the problem of non-smooth and unknown factors in the shaper's operating environment, a forgetting factor is introduced and an adaptive updating algorithm for the forgetting factor is derived based on the scalar gradient between the forgetting factor and the cost function. this method can improve the tracking performance and the final vibration suppression effect of the post-input shaper in an uncertain environment. Finally, the residual vibration suppression effect and convergence time of the post-input shaper with adaptive forgetting factor are verified on a multi-axis motion platform. Compared withthe post adaptive input shaper without forgetting factor and the post adaptive input shaper with constant forgetting factor, the proposed adaptive forgetting factor algorithm significantly improves the post adaptive input shaper, reduces the positioning error of the multiaxis servo system after an emergency stop, and improves the operation efficiency.
As devices around us get more intelligent, new ways of interacting withthem are sought to improve user convenience and comfort. While gesture-controlled systems have existed for some time, they either use additional ...
详细信息
暂无评论