Explainable Goal-driven Agents and Robots - A Comprehensive Review
نویسندگان
چکیده
Recent applications of autonomous agents and robots have brought attention to crucial trust-related challenges associated with the current generation artificial intelligence (AI) systems. AI systems based on connectionist deep learning neural network approach lack capabilities explaining their decisions actions others, despite great successes. Without symbolic interpretation capabilities, they are ‘black boxes’, which renders choices or opaque, making it difficult trust them in safety-critical applications. The recent stance explainability has witnessed several approaches eXplainable Artificial Intelligence (XAI) ; however, most studies focused data-driven XAI applied computational sciences. Studies addressing increasingly pervasive goal-driven sparse at this point time. This paper reviews explainable intelligent robots, focusing techniques for communicating agents’ perceptual functions (e.g., senses, vision) cognitive reasoning beliefs, desires, intentions, plans, goals) humans loop. review highlights key strategies that emphasize transparency, understandability, continual explainability. Finally, presents requirements suggests a road map possible realization effective robots.
منابع مشابه
Self Monitoring, Goal Driven Autonomy Agents
As intelligent systems become a regular part of our everyday lives, robust and safe operation is ever more important. My research focus is to endow agents with the ability to monitor themselves in order to detect when their behavior has exceeded their boundaries. Previously, we have explored different forms of expectations for anomaly detection in agents operating in Real-Time Strategy (RTS) ga...
متن کاملInteractive Multistage Simulation of Goal-Driven Agents
Multistage simulation is employed to help predicting the future actions of collaborating or competing agents, interacting in the mini-world covered by a temporal database. At each stage, their goals are inferred from the current situation, with the help of rules designed to model their behavioural patterns, in turn extracted from records of their past actions. Besides goal-inference rules, the ...
متن کاملTask-space Control of Electrically Driven Robots
Actuators of robot operate in the joint-space while the end-effect or of robot is controlled in the task-space. Therefore, designing a control system for a robotic system in the task-space requires the jacobian matrix information for transforming joint-space to task-space, which suffers from uncertainties. This paper deals with the robust task-space control of electrically driven robot manipula...
متن کاملAre Robots Ready to Deliver Autism Interventions? A Comprehensive Review
This article presents a review of the contemporary robotics research with respect to making robots and human-robot interaction (HRI) useful for autism intervention in clinical settings. Robotics research over the past decade has demonstrated that many children with autism spectrum disorders (ASD) have a strong interest in robots and robot toys and can connect with a robot significantly better t...
متن کاملOntological Knowledge for Goal-Driven Autonomy Agents in Starcraft
Starcraft, a commercial Real-Time Strategy (RTS) game that has enjoyed world-wide popularity (including televised professional matches), is a challenging domain for automated computer agents. Evidence of this difficulty comes not only from characteristics of the game (massive state space, stochastic actions, partial visibility, etc.) but also from three years of competitive entries in tournamen...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: ACM Computing Surveys
سال: 2023
ISSN: ['0360-0300', '1557-7341']
DOI: https://doi.org/10.1145/3564240