The author presents ARMCHAIR, a novel architecture integrating adversarial inverse reinforcement learning and model predictive control for efficient human-robot collaboration.
The author introduces iRoCo as a framework for intuitive robot control using smartwatches and smartphones, optimizing precise control and user movement. The main thesis is that iRoCo offers a promising approach for ubiquitous human-robot collaboration.
Novel architecture ARMCHAIR leverages adversarial inverse reinforcement learning and model predictive control for efficient human-robot collaboration.
Bayes-POMCP optimizes human-robot team performance through adaptive interventions in mixed-initiative settings.
ARMCHAIR leverages adversarial inverse reinforcement learning and model predictive control to optimize trajectories and decisions for efficient human-robot collaboration.
Anticipating human behavior is crucial for robots to interact with humans safely and efficiently, and integrating this capability into mobile manipulation robots can lead to safer navigation and more efficient collaboration in tasks like furniture arrangement.
人間の行動を予測することで、モバイルロボットはより安全なナビゲーションを実現し、家具の移動などの共同作業においても効率を向上させることができる。
Integrating human insights with autonomous sensor data significantly improves dynamic target localization, especially when accounting for and adapting to the evolving reliability of human input.
This paper introduces CoHRT, a novel system designed to facilitate multi-human-robot teamwork in shared workspaces by enabling seamless collaboration, coordination, and communication through a server-client architecture, vision-based tracking, and a user-friendly interface.
CoHRTは、複数の人間とロボットが円滑に共同作業を行うためのシステムであり、チームワーク、協調性、コミュニケーションを強化することで、より効率的で安全なタスク実行を実現します。