The cooperation of a human pilot with an autonomous agent during flight control realizes parallel autonomy. We propose an air-guardian system that facilitates cooperation between a pilot with eye tracking and a parall...
详细信息
ISBN:
(纸本)9781665491907
The cooperation of a human pilot with an autonomous agent during flight control realizes parallel autonomy. We propose an air-guardian system that facilitates cooperation between a pilot with eye tracking and a parallel end-to-end neural control system. Our vision-based air-guardian system combines a causal continuous-depth neural network model with a cooperation layer to enable parallel autonomy between a pilot and a control system based on perceived differences in their attention profiles. The attention profiles for neural networks are obtained by computing the networks' saliency maps (feature importance) through the VisualBackProp algorithm, while the attention profiles for humans are either obtained by eye tracking of human pilots or saliency maps of networks trained to imitate human pilots. When the attention profile of the pilot and guardian agents align, the pilot makes control decisions. Otherwise, the air-guardian makes interventions and takes over the control of the aircraft. We show that our attention-based air-guardian system can balance the trade-off between its level of involvement in the flight and the pilot's expertise and attention. The guardian system is particularly effective in situations where the pilot was distracted due to information overload. We demonstrate the effectiveness of our method for navigating flight scenarios in simulation with a fixed-wing aircraft and on hardware with a quadrotor platform.
In micro-manipulations such as cell manipulation, it is desirable for the operator to feel the haptic sensation of the object. Bilateral control can remotely transmit position and force information between leader and ...
详细信息
ISBN:
(纸本)9798350355376;9798350355369
In micro-manipulations such as cell manipulation, it is desirable for the operator to feel the haptic sensation of the object. Bilateral control can remotely transmit position and force information between leader and follower systems. In this control, the use of a linear motor as a leader and a stacked piezoelectric actuator as a follower has been proposed to achieve micro-scale operation. There is a lot that needs to be clarified about bilateral control when the structure differs between leader and follower systems. In conventional scaled 4-channel (4ch) bilateral control, a theory of oblique coordinate control has been proposed that considers differences in the inertia of leader and follower systems. However, when a piezoelectric actuator is used, the control scheme differs from using two linear motors with different inertias because the structures of the leader and follower systems are entirely different. Another method is scaled admittance bilateral control. However, the control design when structures and inertias of the two systems are different has not yet been clarified. In this paper, a scaled admittance bilateral control using a piezoelectric actuator and a linear motor is constructed. Experiments confirm that the realized scaled admittance bilateral control has the equivalent position and force tracking performances as the conventional scaled 4ch bilateral control using a piezoelectric actuator. Furthermore, the designed scaled admittance bilateral control is more robust to fluctuations in the nominal inertia of the piezoelectric actuator than the conventional scaled 4ch bilateral control.
Propagating uncertainties through nonlinear system dynamics in the context of Stochastic Nonlinear Model Predictive control (SNMPC) is challenging, especially for high-dimensional systems requiring real-time control a...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Propagating uncertainties through nonlinear system dynamics in the context of Stochastic Nonlinear Model Predictive control (SNMPC) is challenging, especially for high-dimensional systems requiring real-time control and operating under time-variant uncertainties such as autonomous vehicles. In this work, we propose an Adaptive SNMPC (aSNMPC) driven by Deep Reinforcement Learning (DRL) to optimize uncertainty handling, constraints robustification, feasibility, and closed-loop performance. To this end, our SNMPC uses Polynomial Chaos Expansion (PCE) for efficient uncertainty propagation, limits its propagation time through an Uncertainty Propagation Horizon (UPH), and transforms nonlinear chance constraints into robustified deterministic ones. We conceive a DRL agent to proactively anticipate upcoming control tasks and to dynamically reduce conservatism by determining the most suitable constraints robustification factor kappa, and to enhance feasibility by choosing optimal UPH length T-u. We analyze the trained DRL agent's decision-making process and highlight its ability to learn context-dependent optimal parameters. We showcase the enhanced robustness and feasibility of our DRL-driven aSNMPC through the real-time motion control task of an autonomous passenger vehicle when confronted with significant time-variant disturbances while achieving a minimum solution frequency of 110Hz. The code used in this research is publicly accessible as open-source software: https://***/bzarr/TUM-control
作者：
Soma, Arun KumarPark University
Department of Information Systems & Business Analytics 8700 NW River Park Dr ParkvilleMO64152 United States
The Aether sensor network is a system of sensors that are used to monitor the environment and detect changes in the atmosphere. It is a system of sensors that are used to monitor the environment and detect changes in ...
详细信息
Probabilistic net-load forecasting in Low-Voltage (LV) distribution networks is essential in light of the increased variability introduced by the widespread integration of renewable energy sources (RES). Various proba...
详细信息
ISBN:
(纸本)9798350318562;9798350318555
Probabilistic net-load forecasting in Low-Voltage (LV) distribution networks is essential in light of the increased variability introduced by the widespread integration of renewable energy sources (RES). Various probabilistic approaches based on neural networks have been proposed to solve this challenge. This study introduces lightweight neural network-based conformal prediction (Conformal-MLPF) for net-load forecasting within an LV power distribution network. It uses Split Conformal prediction to transform a lightweight MLP-based point forecast into a probabilistic forecast. Our validation on two real-life LV substations datasets suggests that the proposed Conformal-MLPF achieves a better tradeoff between forecasting performance and model complexity without requiring restrictive assumptions about data distribution.
With the development of cloud computing, the Internet of Things, and other new technologies, people have put forward higher requirements for virtualization product services and management. Based on the SaaS model, thi...
详细信息
作者：
Cheng, TingLiang, YonghuiXu, QiminZhu, ShanyingDepartment of Automation
Shanghai Jiao Tong University Shanghai 200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240 China
In industrial sites, multiple real-time controlsystems often share computing resources. However, burst computing tasks may lead to the random dropping of controlcomputing subtasks, resulting in control failures and ...
详细信息
Musculoskeletal quadruped robots driven by pneumatic artificial muscles (PAMs) have great softness. Due to the softness, the proprioceptive information of PAMs (e.g. tension) reflects the environmental information. Ho...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Musculoskeletal quadruped robots driven by pneumatic artificial muscles (PAMs) have great softness. Due to the softness, the proprioceptive information of PAMs (e.g. tension) reflects the environmental information. However, how to utilize this information for stable quadrupedal gait has been rarely explored. In this work, we utilized PAM tension for stable locomotion control over uneven terrain. We newly developed a durable tension sensor and proposed tension feedback control for quadruped locomotion over uneven terrain. Our proposed controller stabilizes the trunk posture by modulating the phase of the leg. To verify the effectiveness of the proposed controller, we implement it in a simple quadrupedal model and a musculoskeletal quadruped robot driven by PAMs. Through experiments, with tension feedback, the trunk posture oscillated more stably than that without the feedback. Furthermore, over uneven terrain, the running velocity with tension feedback was higher than that without the feedback in the robot experiment. These successful results will lead to more robust musculoskeletal quadruped robots that can be employed in the real-world environment.
In this study, a Hardware-In-The-Loop (HIL) framework was adopted to support the development of an Electronic control Unit (ECU) for a mini water treatment plant in Lok Dangkaan, Sabah, Malaysia. The purpose was to co...
详细信息
ISBN:
(纸本)9798350372113;9798350372106
In this study, a Hardware-In-The-Loop (HIL) framework was adopted to support the development of an Electronic control Unit (ECU) for a mini water treatment plant in Lok Dangkaan, Sabah, Malaysia. The purpose was to conduct pre-deployment validation and reliability assessments, given that no physical prototype was available, and the deployment site is remotely located. The proposed system consisted of two sets of equipment, each representing a different location of the water storage tank at the target deployment site, with a Raspberry Pi serving as the core embedded controller. A graphical user interface (GUI) was employed to exhibit the current water level and the activation of pumps at each location. Information was relayed via the MQTT protocol, which was configured for the area. Results indicated a 100% prototype functionality and smooth connectivity between components were achieved. The GUI has also been responsive in accordance with the expected dynamics of water inflow and outflow. Future work may be directed towards integrating machine learning capabilities to analyze water usage trends and enhance facility maintenance, utilizing data recorded from the proposed HIL system.
The Industrial Internet of Things (IIoT) has become a crucial technology driving the transformation of manufacturing towards intelligence. Traditional industrial networks primarily focus on data collection, whereas em...
详细信息
暂无评论