the proceedings contain 68 papers. the topics discussed include: research on storage AGV system based on cloud edge collaboration;the experimental research about the human back kinematic characteristics with differenc...
ISBN:
(纸本)9798350302776
the proceedings contain 68 papers. the topics discussed include: research on storage AGV system based on cloud edge collaboration;the experimental research about the human back kinematic characteristics with difference stride;reducing emissions through AdBlue tank temperature control in diesel engines with SCR system;a fault handling scheme for remote guidance of autonomous quick rendezvous and docking;development of online monitoring system for mine hoist cage;dynamic differential flatness of cable elasticity of a cable-driven parallel manipulator;a launch device for autonomous underwater vehicle used in water conveyance tunnel;heterogeneous graph convolutional network for visual reinforcement learning of action detection;detection of river floating waste based on decoupled diffusion model;and consensus of uncertain Euler-Lagrange multi-agent systems under switching digraphs and disturbances.
the proceedings contain 50 papers. the topics discussed include: an improved rapidly-exploring random tree star algorithm for manipulator path planning;a robust robot system via multi-sensor fusion localization and op...
ISBN:
(纸本)9798350327656
the proceedings contain 50 papers. the topics discussed include: an improved rapidly-exploring random tree star algorithm for manipulator path planning;a robust robot system via multi-sensor fusion localization and optimized path planning;design of a medical expert system to consult selecting an examination department and to provide the path signal for a mobile robot to lead patients to the consulted department;joint delivery path optimization based on improved particle swarm optimization algorithm;slipping control of tracked vehicles in shallow water areas;towards multimodal multitask scene understanding models for indoor mobile agents;gearbox fault diagnosis based on local domain adaptation network under different working conditions;coordinated tuning of slurry shield control parameters based on reinforcement learning;and whole body motion control strategy of humanoid robot based on double-layer quadratic optimization.
Soft robotics promises new opportunities for solving problems that were limited by rigid robots due to their compliant physical structure. Pneumatic Soft Actuators (PSA) are a class of soft robots that have gained pop...
详细信息
the proceedings contain 46 papers. the topics discussed include: motion control of liquid containers with slosh constraints during high-speed three-dimensional transfer;a hybrid Bayesian network structure learning alg...
ISBN:
(纸本)9798350345650
the proceedings contain 46 papers. the topics discussed include: motion control of liquid containers with slosh constraints during high-speed three-dimensional transfer;a hybrid Bayesian network structure learning algorithm in equivalence class space;a comparative study on grid-based and non-grid-based path planning algorithm;Bayesian network structure learning algorithm based on score increment and reduction;toxicity detection using state of the art natural language methodologies;research on deep spatio-temporal model and its application in situation prediction;an end-to-end pose estimation network for multiscale space non-cooperative objects;better multi-step time series prediction using sparse and deep echo state network;a digital twin-based production-maintenance joint scheduling framework with reinforcement learning;a feature structure based interpretability evaluation approach for deep learning;pattern recognition of partial discharge faults using convolutional neural network (CNN);and automatic detection of natural disaster effect on paddy field from satellite images using deep learning techniques.
Soft robotics promises new opportunities for solving problems that were limited by rigid robots due to their compliant physical structure. Pneumatic Soft Actuators (PSA) are a class of soft robots that have gained pop...
Soft robotics promises new opportunities for solving problems that were limited by rigid robots due to their compliant physical structure. Pneumatic Soft Actuators (PSA) are a class of soft robots that have gained popularity due to their cost-effective manufacturing and high force-generating capability. Due to their highly nonlinear dynamics, accurate prediction of their response to input pressure (curvature) as well as force output is challenging. Artificial Neural Networks were employed to this effect. this work shows a comparative analysis of three variants of the recurrent neural network used in this paper for predicting the behavior of soft robotic actuators. Each network was trained using the same data set to predict the position, curvature, and applied force by the soft robotics on an external force. the result shows the different performance of the three models, evaluating them using Mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). the Long Short-term Memory (LSTM) model outperformed boththe Gated Recurrent Unit (GRU) and Recurrent Neural Network (RNN) models, producing the lowest error in the three metrics.
the proceedings contain 85 papers. the topics discussed include: a hybrid method for INS/GPS integrated navigation system based on the improved Karman filter and back propagation neural network;development of Simulink...
ISBN:
(纸本)9798350344721
the proceedings contain 85 papers. the topics discussed include: a hybrid method for INS/GPS integrated navigation system based on the improved Karman filter and back propagation neural network;development of Simulink-based physical experiment platform for EtherCAT bipedal robots;a biogeography-based optimization algorithm with heuristics for distributed multiproduct scheduling problem;research on low energy consumption AC system control strategy of battery electric vehicles;flyback converter modeling and overload control characteristics for power supply based on state space averaging;a simple confidence-supervised model for high resolution defect recognition;research and development of intelligent warehouse management system based on RFID technology;research on methods of vehicle image retrieval in expressway scenarios based on deep learning neural network;and motion simulation control system of detecting robot based on digital twin.
the proceedings contain 16 papers. the topics discussed include: training a neural network to observe the assembly mode of parallel robots;control of variable-size wheeled mobile robots;prototype of an intelligent tex...
ISBN:
(纸本)9798350330519
the proceedings contain 16 papers. the topics discussed include: training a neural network to observe the assembly mode of parallel robots;control of variable-size wheeled mobile robots;prototype of an intelligent textile based robot skin to expand potential applications for cobot’s;classification of human postures;overview of synthetic data generation for computer vision in industry;advancements and innovations in U-Net for enhanced medical image segmentation: a review;optimum design of bottom stirring impeller for cosmetics manufacturing;a study of vibration signal feature extraction for bone drilling layer classification;exploring the potential of a vertical takeoff and landing flying car;descent vehicle movement control by the angular position change method payload;and development of an innovative air-ground carrier platform for multi-mode drones.
the proceedings contain 76 papers. the topics discussed include: nonlinear identification and time-frequency domain analysis of corticomuscular responses during card-grabbing using the NARMAX method;working-hour calcu...
ISBN:
(纸本)9781665481168
the proceedings contain 76 papers. the topics discussed include: nonlinear identification and time-frequency domain analysis of corticomuscular responses during card-grabbing using the NARMAX method;working-hour calculation of construction machinery based on outlier analysis;workshop management and control system based on digital twin;collision cone based collision avoidance for hexa-rotors;double condyles contact force estimation of knee joint based on hill-type model;moving object flexible grasping based on deep reinforcement learning;design and fabrication of an Internet of things enhanced digital track gauge;and volume estimation of harbor engineering objects using underwater three-dimensional sonar.
In this paper, we propose an open-source lunar rover simulator integrated with a reinforcement learning framework. We incorporate lunar environmental effects in our simulator to enhance the rover locomotion realism wh...
详细信息
ISBN:
(纸本)9798350350319;9798350350302
In this paper, we propose an open-source lunar rover simulator integrated with a reinforcement learning framework. We incorporate lunar environmental effects in our simulator to enhance the rover locomotion realism while employing PyBullet to simulate the dynamics of a multi-degree-of-freedom planetary rover. We also extend our lunar rover simulator to interface with a reinforcement learning framework using OpenAI Gym environment and a compatible training workflow. We demonstrate the success of this integration through an autonomous rover navigation task on the lunar environment in our simulator using two reinforcement learning algorithms, DDPG and TD3. the lunar rover simulator is available at https://***/assawayut/LunarRoverSim and an accompanying video can be accessed at https://***/watch?v=8HMqAkDbpqI.
Underwater robots, despite their wide applications, struggle with localization and navigation in GPS-free environments, a problem potentially solvable by acoustic sensor modules. However, to counteract sensor bias cau...
详细信息
暂无评论