Learning to Navigate in Complex Environments

Mirowski, Piotr; Pascanu, Razvan; Romano, Pietro; Soyer, Hubert; Ballard, Andrew J.; Banino, Andrea; Denil, Misha; Goroshin, Ross; Sifre, Laurent; Kavukcuoglu, Koray; Kumaran, Dharshan; Hadsell, Raia

doi:10.48550/arxiv.1611.03673

Cited by 151 publications

(204 citation statements)

References 0 publications

Supporting

Mentioning

203

Contrasting

Order By: Relevance

“…Robotic navigation. Robots often use visual signals to navigate in novel environments [64,65,66,67]. While vision is often a reliable cue for depth estimation, there are many situations where it is unavailable (e.g.…”

Section: Static Motionmentioning

confidence: 99%

Structure from Silence: Learning Scene Structure from Ambient Sound

Chen¹,

Hu²,

Owens³

2021

Preprint

View full text Add to dashboard Cite

https://ificl.github.io/structure-from-silence (a) Quiet Campus dataset (b) Depth estimation (c) Multimodal self-supervision ( ) , ( ) , (a) Quiet Campus dataset (b) Depth estimation (c) Multimodal self-supervision Figure 1: What can ambient sound tell us about 3D scene structure? (a) We collect an "in-the-wild" dataset of paired audio and RGB-D recordings from quiet indoor scenes. (b) Given audio from a scene, we estimate distance to a wall. (c) We use this ambient sound to learn audio-visual representations through self-supervision.

show abstract

Section: Static Motionmentioning

confidence: 99%

Structure from Silence: Learning Scene Structure from Ambient Sound

Chen¹,

Hu²,

Owens³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Generally speaking, those methods utilize visual observations as input and directly predict moving actions. Mirowski et al [38] introduce prediction and loop closure classification tasks to improve navigation performance in 3D maze environments. Kahn et al [28] propose a method to build a model of the environment by a self-supervised method.…”

Section: Visual Navigation With Rlmentioning

confidence: 99%

Agent-Centric Relation Graph for Object Visual Navigation

Hu¹,

Wu²,

Lv³

et al. 2021

Preprint

View full text Add to dashboard Cite

Object visual navigation aims to steer an agent towards a target object based on visual observations of the agent. It is highly desirable to reasonably perceive the environment and accurately control the agent. In the navigation task, we introduce an Agent-Centric Relation Graph (ACRG) for learning the visual representation based on the relationships in the environment. ACRG is a highly effective and reasonable structure that consists of two relationships, i.e., the relationship among objects and the relationship between the agent and the target. On the one hand, we design the Object Horizontal Relationship Graph (OHRG) that stores the relative horizontal location among objects. Note that the vertical relationship is not involved in OHRG, and we argue that OHRG is suitable for the control strategy. On the other hand, we propose the Agent-Target Depth Relationship Graph (ATDRG) that enables the agent to perceive the distance to the target. To achieve ATDRG, we utilize image depth to represent the distance. Given the above relationships, the agent can perceive the environment and output navigation actions. Given the visual representations constructed by ACRG and position-encoded global features, the agent can capture the target position to perform navigation actions. Experimental results in the artificial environment AI2-Thor demonstrate that ACRG significantly outperforms other state-of-the-art methods in unseen testing environments.

show abstract

“…Our solution is one type of transfer learning, where the goal is specifically to pre-train one specific part of the policy function to allow faster learning for producing assisting actions. When using auxiliary tasks, the common representation among the original task and auxiliary tasks can be improved by adding extra auxiliary heads to the representation [9,13,26]. In our solution, instead of adding an extra auxiliary head to the common representation, the helper agent is pre-trained on the task of making predictions of the goal-driven agents' actions in self-supervised manner or goals in a supervised manner.…”

Section: Related Workmentioning

confidence: 99%

Learning to Assist Agents by Observing Them

Keurulainen¹,

Westerlund²,

Kaski³

et al. 2021

Preprint

View full text Add to dashboard Cite

The ability of an AI agent to assist other agents, such as humans, is an important and challenging goal, which requires the assisting agent to reason about the behavior and infer the goals of the assisted agent. Training such an ability by using reinforcement learning usually requires large amounts of online training, which is difficult and costly. On the other hand, offline data about the behavior of the assisted agent might be available, but is non-trivial to take advantage of by methods such as offline reinforcement learning. We introduce methods where the capability to create a representation of the behavior is first pre-trained with offline data, after which only a small amount of interaction data is needed to learn an assisting policy. We test the setting in a gridworld where the helper agent has the capability to manipulate the environment of the assisted artificial agents, and introduce three different scenarios where the assistance considerably improves the performance of the assisted agents.

show abstract

Learning to Navigate in Complex Environments

Cited by 151 publications

References 0 publications

Structure from Silence: Learning Scene Structure from Ambient Sound

Structure from Silence: Learning Scene Structure from Ambient Sound

Agent-Centric Relation Graph for Object Visual Navigation

Learning to Assist Agents by Observing Them

Contact Info

Product

Resources

About