Ensuring safe interactions in human-centric environments requires robots to understand and adhere to constraints recognized by humans as "common sense" (e.g., "moving a cup of water above a laptop is un...
详细信息
Ensuring safe interactions in human-centric environments requires robots to understand and adhere to constraints recognized by humans as "common sense" (e.g., "moving a cup of water above a laptop is unsafe as the water may spill" or "rotating a cup of water is unsafe as it can lead to pouring its content"). Recent advances in computer vision and machine learning have enabled robots to acquire a semantic understanding of and reason about their operating environments. While extensive literature on safe robot decision-making exists, semantic understanding is rarely integrated into these formulations. In this work, we propose a semantic safety filter framework to certify robot inputs with respect to semantically defined constraints (e.g., unsafe spatial relationships, behaviors, and poses) and geometrically defined constraints (e.g., environment-collision and self-collision constraints). In our proposed approach, given perception inputs, we build a semantic map of the 3D environment and leverage the contextual reasoning capabilities of large language models to infer semantically unsafe conditions. These semantically unsafe conditions are then mapped to safe actions through a control barrier certification formulation. We demonstrate the proposed semantic safety filter in teleoperated manipulation tasks and with learned diffusion policies applied in a real-world kitchen environment that further showcases its effectiveness in addressing practical semantic safety constraints. Together, these experiments highlight our approach's capability to integrate semantics into safety certification, enabling safe robot operation beyond traditional collision avoidance.
The purpose of task-oriented robot cognitive manipulation planning is to enable robots to select appropriate actions to manipulate appropriate parts of an object according to different tasks, so as to complete the hum...
详细信息
The purpose of task-oriented robot cognitive manipulation planning is to enable robots to select appropriate actions to manipulate appropriate parts of an object according to different tasks, so as to complete the human-like task execution. This ability is crucial for robots to understand how to manipulate and grasp objects under given tasks. This article proposes a task-oriented robot cognitive manipulation planning method using affordance segmentation and logic reasoning, which can provide robots with semantic reasoning skills about the most appropriate parts of the object to be manipulated and oriented by tasks. Object affordance can be obtained by constructing a convolutional neural network based on the attention mechanism. In view of the diversity of service tasks and objects in service environments, object/task ontologies are constructed to realize the management of objects and tasks, and the object-task affordances are established through causal probability logic. On this basis, the Dempster-Shafer theory is used to design a robot cognitive manipulation planning framework, which can reason manipulation regions' configuration for the intended task. The experimental results demonstrate that our proposed method can effectively improve the cognitive manipulation ability of robots and make robots preform various tasks more intelligently.
A potential barrier to an effective human-machine team is the mismatch between the learning dynamics of each teammate. humans often master new cognitive-motor tasks quickly, but not instantaneously. In contrast, artif...
详细信息
ISBN:
(纸本)9783031054570;9783031054563
A potential barrier to an effective human-machine team is the mismatch between the learning dynamics of each teammate. humans often master new cognitive-motor tasks quickly, but not instantaneously. In contrast, artificial systems often solve new tasks instantaneously (e.g., knowledge-based planning agents) or learn much more slowly than humans (e.g., reinforcement learning agents). In this work, we present our ongoing work on a robotic control architecture that blends planning and memory to produce more human-like learning dynamics. We empirically assess current implementations of four main components in this architecture: object manipulation, full-body motor control, robot vision, and imitation learning. Assessment is conducted using a simulated humanoid robot performing a maintenance task in a virtual tabletop setting. Finally, we discuss the prospects for using this learning architecture with human teammates in virtual and ultimately physical environments.
Physical human-robot interaction is fundamental to exploiting the capabilities of robots in tasks and environments where robots have limited cognition or comprehension and is virtually ubiquitous for robotic manipulat...
详细信息
Physical human-robot interaction is fundamental to exploiting the capabilities of robots in tasks and environments where robots have limited cognition or comprehension and is virtually ubiquitous for robotic manipulation in highly unstructured environments, as are found in surgery. A critical aspect of physical human-robot interaction in these cases is controlling the robot so that the individual human and robot competencies are maximized, while guaranteeing user, task, and environment safety. Dissipative control precludes dangerous forcing of a shared tool by the robot, ensuring safety;however, it typically suffers from poor control fidelity, resulting in reduced task accuracy. In this study, a novel, rigorously formalized, n-dimensional dissipative control strategy is proposed that employs a new technique called "energy redirection" to generate control forces with increased fidelity while remaining dissipative and safe. Experimental validation of the method, for complete pose control, shows that it achieves a 90% reduction in task error compared with the current state of the art in dissipative control for the tested applications. The findings clearly demonstrate that the method significantly increases the fidelity and efficacy of dissipative control during physical human-robot interaction. This advancement expands the number of tasks and environments into which safe physical human-robot interaction can be employed effectively.
Research shows that children construct much of their knowledge through active manipulation of the environment, which allows them to connect abstract concepts to observable outcomes. Despite these findings, although th...
详细信息
ISBN:
(纸本)9781605583952
Research shows that children construct much of their knowledge through active manipulation of the environment, which allows them to connect abstract concepts to observable outcomes. Despite these findings, although the integration of novel pedagogical technologies into classroom settings has begun, the technologies predominantly have focused on instruction in virtual contexts. To date, however, little is known about novel technologies that step outside of the virtual realm into the physical classroom, thereby leveraging findings on embodied mathematical cognition to influence educational practices. As a first step in filling this gap, we present the Active learning Environment with robotics Tangibles (ALERT) framework. Our system relies on human-robot interaction and tangible instruction to motivate and trigger learning in students through a variety of activities that integrate play and instruction in mixed reality environments. Here we describe some of the activities supported by ALERT, and discuss pl ans for evaluating the pedagogical utility of the system Copyright 2009 ACM 978-.
Summary form only given. In recent years we have seen tremendous advances in the mechatronic, sensing and computational infrastructure of robots, enabling them to act faster, stronger and more accurately than humans d...
Summary form only given. In recent years we have seen tremendous advances in the mechatronic, sensing and computational infrastructure of robots, enabling them to act faster, stronger and more accurately than humans do. Yet, when it comes to accomplishing manipulation tasks in everyday settings, robots often do not even reach the sophistication and performance of young children. This is partly due to humans having developed their brains into computational and control devices that facilitate knowledge-informed decision making, perspective taking, envisioning activities and their consequences, and predictive control. Brains orchestrate these learning and reasoning mechanisms in order to produce flexible, adaptive, and reliable behavior in real-time. Household chores are an activity domain where the superiority of the cognitive mechanisms in the brain and their role in competent activity control is particularly evident.
暂无评论