Multi-Object Navigation in real environments using hybrid policies
Assem Sadek,Guillaume Bono,Boris Chidlovskii,Atilla Baskurt,Christian Wolf,Assem Sadek,Guillaume Bono,Boris Chidlovskii,Atilla Baskurt,Christian Wolf
Navigation has been classically solved in robotics through the combination of SLAM and planning. More recently, beyond waypoint planning, problems involving significant components of (visual) high-level reasoning have been explored in simulated environments, mostly addressed with large-scale machine learning, in particular RL, offline-RL or imitation learning. These methods require the agent to le...
