This paper addresses the safety control problem for robotic systems under nonparametric uncertainty conditions by proposing a control scheme based on Gaussian Process Regression (GPR). Initially, leveraging historical...
详细信息
ISBN:
(纸本)9798350385731;9798350385724
This paper addresses the safety control problem for robotic systems under nonparametric uncertainty conditions by proposing a control scheme based on Gaussian Process Regression (GPR). Initially, leveraging historical data collected online, the GPR is employed to learn nonparametric uncertainty and time-varying disturbances. Subsequently, by employing a feedback linearization based on Lyapunov theory, we can obtain the system Global Uniform Ultimate Boundedness (GUUB). Furthermore, considering safety constraints, an additional layer is introduced to the feedback controller using Control Barrier Functions (CBF). The control input is minimally adjusted based on Quadratic Programming (QP) to satisfy optimization requirements while maintaining safety. The paper establishes, in a high probability sense, the boundedness of the closed-loop system and the forward invariance of the state safety domain. The efficacy of the proposed control approach is validated through simulation on trajectory tracking and obstacle avoidance under nonparametric uncertainty. The results confirm the validity of the control approach in handling safety and performance concerns simultaneously.
This research addresses the challenge of ensuring the safe operation of Robotic Autonomous systems (RAS) in highly regulated domains through the formalisation of safety requirements, with a specific focus on the UK nu...
详细信息
ISBN:
(纸本)9798350395129;9798350395112
This research addresses the challenge of ensuring the safe operation of Robotic Autonomous systems (RAS) in highly regulated domains through the formalisation of safety requirements, with a specific focus on the UK nuclear safety regime as a use case of our approach that serves as a feasibility study. Driven by the growing need to deploy robots for safety and efficiency in hazardous environments, we seek to develop a systematic approach to address this challenge comprehensively. The main objectives include exploring how to derive formal properties, which are practical to verify, from functional safety requirements for RAS within the context of RE. The development of a rules-based Safety system is proposed to demonstrate this approach, which aims to be compliant with safety standards and relevant good practice. The proposed framework defines safety requirements based on existing safety protocols and industry practice. This work involves eliciting and formalising requirements for the Safety system, and integrating it with an autonomous robot. Through a real-world application involving an inspection robot in the UK nuclear industry, this research aims to demonstrate the practicality of this approach. we emphasise the importance of safety assurance throughout the life cycle of RAS, from hazard analysis to requirements elicitation and beyond.
Humans have spatiotemporal limitations. Robotic avatar technology enables the expansion of an individual's innate physical characteristics, physical capabilities, and perceptual and cognitive abilities. Our resear...
Safety issues related to autonomous vehicles are of great concern both in the academy and industry, identifying the braking system performance as a crucial research field. In this work, an autonomous braking system ba...
详细信息
Amputees use prosthetic devices to perform activities of daily living. However, some users reject their devices due to the lack of usability or high cognitive workload. Although virtual reality has been studied in thi...
详细信息
This paper presents a controller to adapt to the massive variation, disturbances, and unknown system parameters on a Gough-Stewart platform. This mechanism refers to a parallel robot with six legs and actuators that c...
详细信息
Large Language Models (LLMs) have gained popularity since the release of ChatGPT in 2022. These systems utilize Artificial Intelligence (AI) algorithms to analyze natural language, enabling users to have sophisticated...
详细信息
Visual illusions, as powerful tools for revealing the strategies and limitations of brain visual processing, have garnered attention in neural network research. This study aims to investigate the performance of variou...
详细信息
This paper focuses on a network framework where a team of elements endeavors to traverse from an origin to a destination, aiming to minimize the maximum risk along their path. Within this network, each link is charact...
详细信息
ISBN:
(纸本)9798350358513;9798350358520
This paper focuses on a network framework where a team of elements endeavors to traverse from an origin to a destination, aiming to minimize the maximum risk along their path. Within this network, each link is characterized by a specific exposure to risk, with the potential for risk amplification when encountering another team of diverse elements seeking to inflict damage on the same link. The study employs the method of successive averages to optimize the path choice, emphasizing risk mitigation and control strategies. Results are demonstrated on an exemplificative network, showcasing the convergence of the chosen path through the iterative application of the method of successive averages. This approach provides valuable insights into navigating complex networks while considering dynamic risk factors, offering practical implications for system-of-systemsengineering and risk-aware decision-making.
While the use of machine learning techniques in high stake fields, such as medical diagnosis and criminal justice, has been increasing in recent years, concerns have been raised regarding the lack of transparency and ...
详细信息
暂无评论