Robust Person Guidance by Using Online POMDPs
نویسندگان
چکیده
The paper considers a guiding task in which a robot has to guide a person towards a destination. A robust operation requires to consider uncertain models on the person motion and intentions, as well as noise and occlusions in the sensors employed for the task. Partially Observable Markov Decision Processes (POMDPs) are used to model the task. The paper describes an enhancement on online POMDP solvers that allow to apply them to larger problems. The algorithm is used to control the robot in real-time for the guiding application. Results in simulation illustrate the approach.
منابع مشابه
The Role of online Career Counseling based on the Guidance Approach in Career Adaptability of Nurses
Introduction: lack of qualified nurses is a global concern that endangers therapeutic quality. Studies show that in addition to attracting and selecting qualified nurses, their maintenance is another problem for hospitals. The objective of this study is to determine the effect of online career counseling based on guidance approach on career adaptability of nurses. Method: this quasi-experimenta...
متن کاملA Robust Feedforward Active Noise Control System with a Variable Step-Size FxLMS Algorithm: Designing a New Online Secondary Path Modelling Method
Several approaches have been introduced in literature for active noise control (ANC)systems. Since Filtered-x-Least Mean Square (FxLMS) algorithm appears to be the best choice as acontroller filter. Researchers tend to improve performance of ANC systems by enhancing andmodifying this algorithm. This paper proposes a new version of FxLMS algorithm. In many ANCapplications an online secondary pat...
متن کاملDecision-Theoretic Planning with Person Trajectory Prediction for Social Navigation
Robots navigating in a social way should reason about people intentions when acting. For instance, in applications like robot guidance or meeting with a person, the robot has to consider the goals of the people. Intentions are inherently non-observable, and thus we propose Partially Observable Markov Decision Processes (POMDPs) as a decisionmaking tool for these applications. One of the issues ...
متن کاملAEMS: An Anytime Online Search Algorithm for Approximate Policy Refinement in Large POMDPs
Solving large Partially Observable Markov Decision Processes (POMDPs) is a complex task which is often intractable. A lot of effort has been made to develop approximate offline algorithms to solve ever larger POMDPs. However, even stateof-the-art approaches fail to solve large POMDPs in reasonable time. Recent developments in online POMDP search suggest that combining offline computations with ...
متن کاملA Robust Controller with Online Authority Transformation for Dual User Haptic Training System
In this study, a force reflection control structure is developed for the surgery training haptic system. In the surgery training haptic system, the surgical operation is cooperatively performed by a trainer and a trainee. The participation of each surgeon in the operation is established through their own haptic consoles. Although the operation is primarily performed by the trainee, the trainer ...
متن کامل