Investigating Inverse Reinforcement Learning during Rapid Aiming Movement in Extended Reality and Human-Robot Interaction

Rapid aiming movement involves quick, accurate, pre-programmed motions used in the context of human-computer and human-robot interaction. It incorporates target forecasting to minimize the duration of tasks requiring rapid aiming. Applications include predicting target icons in UI design, driver intent in automotive technology, and human intent during human-robot collaboration. Conventional approaches often fail to capture human preferences accurately, leading to low prediction accuracy. This work explores an Inverse Reinforcement Learning (IRL)-based system for forecasting human hand movements and intended targets during rapid aiming. Sampling-based Maximum Entropy IRL (SMEIRL) with a sampler and Maximum Entropy Deep IRL (MEDIRL) algorithms were evaluated for prediction accuracy. The proposed sampler efficiently generates sample trajectories for rapid aiming tasks. User studies were conducted to assess target prediction during two tasks involving rapid aiming movement: (1) Pointing in Virtual Reality (VR) and Mixed Reality (MR), and (2) Human-robot handovers. A multimodal target prediction algorithm was analyzed for swift and accurate anticipation of the intended target, considering both hand and eye gaze. Results demonstrate that the proposed approach achieves a prediction accuracy of 98% in MR and 96% in VR for the pointing task using SMEIRL. During human-robot handover task, prediction accuracy using MEDIRL reached 99.9% when less than 20% and 40% of the task was left using only hand motion or both hand and eye gaze, respectively, surpassing state-of-the-art methods using Path Integral-IRL (PI-IRL), Recurrent Neural Network-Inverse Kinematics-Modified Kalman Filtering (RNNIK-MKF), Bayesian Predictor for Human Motion Trajectory (BP-HMT), and Classical kinematics of motion ( \(CM_{k=5}\) )

Acoustics · Human–computer interaction · Human–robot interaction · Physics · Reinforcement · Reinforcement learning · Robot · Computer Science · Motor Control and Adaptation · Muscle activation and electromyography studies · Psychology · Robot Manipulation and Learning · Social Psychology · Artificial Intelligence

• The information capacity of the human motor system in controlling the amplitude of movement.

  Paul M Fitts•Journal of Experimental…•1954

  Añadir item

• Variable Autonomy through Responsible Robotics

  Open Access•Tyler Reinmund, Pericle Salvini et al.•ACM Transactions on Human-Robot…•2024

  Añadir item

• Batch Active Learning of Reward Functions from Human Preferences

  Open Access•Erdem Biyik, Nima Anari et al.•ACM Transactions on Human-Robot…•2024

  Añadir item

• A century later

  Digby Elliott, Werner F Helsen et al.•Psychological Bulletin•2001

  Añadir item