Embodied Visual Navigation With Automatic Curriculum Learning in Real Environments

Morad, Steven; Mecca, Roberto; Poudel, Rudra P. K.; Liwicki, Stephan; Cipolla, Roberto

doi:10.1109/lra.2020.3048662

Cited by 26 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the success of RL algorithms for solving challenging control tasks [13], [80], [213], [214], Zhang et al employ successor representation in learning to achieve quick adaptation. Morad et al [215] present an indoor object-driven navigation method named NavACL that uses automatic curriculum learning and is easily generalized to new environments and targets. Kahn et al [216] adopt multitask learning and off-policy RL learning to learn directly from real-world events.…”

Section: Methods For Real-world Navigationmentioning

confidence: 99%

Deep Learning for Embodied Vision Navigation: A Survey

Zhu,

Lee

et al. 2021

Preprint

View full text Add to dashboard Cite

The problem of embodied vision navigation attracts rising attention from the community due to its wide application in autonomous driving, vacuum cleaner, and rescue robot. To accomplish embodied vision navigation requires various intelligent skills, such as exploration, mapping, and planning, visual recognition and reasoning, etc. Moreover, building a robot that observes like a human, thinks like a human, and acts like a human helps the community to know how intelligence really is. 3D simulation technology provides a large scale of data to simulate the real-world environment, which enables researchers to train and test the embodied visual navigation model within it. The robustness of deep learning methods empowered the embodied navigation agents to accomplish diverse tasks. However, embodied navigation is still in its infancy due to a lot of challenges, like learning a robust policy from partially observed visual input, learning to exploration in navigation, accomplishing natural language navigation tasks, adapting to the real-world environment, etc. Recently, numerous works have been proposed to tackle different challenges in this area. To give a promising direction for future research, in this paper, we present a comprehensive review of embodied navigation tasks and the recent progress in deep learning-based methods.

show abstract

Section: Methods For Real-world Navigationmentioning

confidence: 99%

Deep Learning for Embodied Vision Navigation: A Survey

Zhu,

Lee

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…• Step 1 -Define State Type: When assessing an RL task, it is essential to comprehend the state that can be obtained from the surrounding environment. For instance, some navigation tasks simplify the environment's states using gridcell representations [68,73,93], where the agent has a limited and predetermined set of states, whereas in other tasks, the environment can have unlimited states [34,38,40]. Therefore, this steps involves a decision between limited vs. unlimited states.…”

Section: Problem Formulation and Algorithm Selectionmentioning

confidence: 99%

Autonomous Unmanned Aerial Vehicle navigation using Reinforcement Learning: A systematic review

AlMahamid

Grolinger

2022

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

“…Bajcsy et al [38] make a convincing argument why any research on robot navigation necessarily has to include active perception, to quote their conclusion: "An agent is an active perceiver if it knows why it wishes to sense, and then chooses what to perceive, and determines how, when and where to achieve that perception". An active solution for autonomous automotive navigation has been proposed by Kendall et al [39], whereas an active approach for robot navigation was presented by Morad et al [40]. The addition of a social aspect is another dimension that is very hard to learn in a passive way: it is challenging to definitively decide on a "correct" motion in relation to humans since they react differently to the presence of the robot and have their own specific behaviours as well [41], [4], [42].…”

Section: Active Vs Passive Visionmentioning

confidence: 99%

A Survey on Human-aware Robot Navigation

Möller¹,

Furnari²,

Battiato³

et al. 2021

Preprint

View full text Add to dashboard Cite

Intelligent systems are increasingly part of our everyday lives and have been integrated seamlessly to the point where it is difficult to imagine a world without them. Physical manifestations of those systems on the other hand, in the form of embodied agents or robots, have so far been used only for specific applications and are often limited to functional roles (e.g. in the industry, entertainment and military fields). Given the current growth and innovation in the research communities concerned with the topics of robot navigation, human-robot-interaction and human activity recognition, it seems like this might soon change. Robots are increasingly easy to obtain and use and the acceptance of them in general is growing. However, the design of a socially compliant robot that can function as a companion needs to take various areas of research into account. This paper is concerned with the navigation aspect of a socially-compliant robot and provides a survey of existing solutions for the relevant areas of research as well as an outlook on possible future directions.

show abstract

Embodied Visual Navigation With Automatic Curriculum Learning in Real Environments

Cited by 26 publications

References 33 publications

Deep Learning for Embodied Vision Navigation: A Survey

Deep Learning for Embodied Vision Navigation: A Survey

Autonomous Unmanned Aerial Vehicle navigation using Reinforcement Learning: A systematic review

A Survey on Human-aware Robot Navigation

Contact Info

Product

Resources

About