Deep Reinforcement Learning for Instruction Following Visual Navigation in 3D Maze-Like Environments
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2020.2965857
Abstract: In this work, we address the problem of visual navigation by following instructions. In this task, the robot must interpret a natural language instruction in order to follow a predefined path in a possibly unknown… read more here.
Keywords: visual navigation; maze like; instruction following; like environments ... See more keywords
DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2022.3193254
Abstract: Language-guided Embodied AI benchmarks requiring an agent to navigate an environment and manipulate objects typically allow one-way communication: the human user gives a natural language command to the agent, and the agent can only follow… read more here.
Keywords: embodied instruction; dialogue enabled; dialfred dialogue; agent ... See more keywords