A Cordial Sync: Going Beyond Marginal Policies for Multi-agent Embodied Tasks

Jain, Unnat; Weihs, Luca; Kolve, Eric; Farhadi, Ali; Lazebnik, Svetlana; Kembhavi, Aniruddha; Schwing, Alexander G.

doi:10.1007/978-3-030-58558-7_28

Cited by 37 publications

(43 citation statements)

References 72 publications

(94 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The community has built several indoor navigation simulators [41,57,40,27] on top of photo-realistic scans of 3D environments [27,6,47,56,55]. To test a robot's ability to perceive, navigate and interact with the environment, the community has also introduced several tasks [57,5,45,10,52,36,3,28,48,22,21,51,16,34,33,31,32] and benchmarks. Specifically, Batra et al [5] introduce evaluation details for the task of Object Navigation, requiring the agent to navigate to a given object class instead of a final point-goal.…”

Section: Related Workmentioning

confidence: 99%

“…Thomason et al [48] introduce Vision-and-Dialog Navigation that requires back-and-forth communication in order to reach the desired location. Jain et al [22,21] develop FurnLift and FurnMove to study visual multi-agent navigation. While these tasks differ in their setup, each of them requires the agent to navigate accurately in an environment.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation

Zhao¹,

Agrawal

Batra

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

It is fundamental for personal robots to reliably navigate to a specified goal. To study this task, PointGoal navigation has been introduced in simulated Embodied AI environments. Recent advances solve this PointGoal navigation task with near-perfect accuracy (99.6% success) in photo-realistically simulated environments, assuming noiseless egocentric vision, noiseless actuation and most importantly, perfect localization. However, under realistic noise models for visual sensors and actuation, and without access to a "GPS and Compass sensor," the 99.6%-success agents for PointGoal navigation only succeed with 0.3%. 1 In this work, we demonstrate the surprising effectiveness of visual odometry for the task of PointGoal navigation in this realistic setting, i.e., with realistic noise models for perception and actuation and without access to GPS and Compass sensors. We show that integrating visual odometry techniques into navigation policies improves the state-of-the-art on the popular Habitat PointNav benchmark by a large margin, improving success from 64.5% to 71.7% while executing 6.4 times faster.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation

Zhao¹,

Agrawal

Batra

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Multi-Agent RL. To efficiently learn policies in multi-agent systems, a variety of multi-agent RL algorithms have been proposed [4][5][6][7][8][9][10][11][12][13][31][32][33][34]. For example, to cope with nonstationarity, 'Multi-agent Actor-critic' [4] uses a centralized critic which operates on all agents' observations and actions.…”

Section: Related Workmentioning

confidence: 99%

Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning

Liu¹,

Ren²,

Yeh³

et al. 2021

Preprint

View full text Add to dashboard Cite

Solving complex real-world tasks, e.g., autonomous fleet control, often involves a coordinated team of multiple agents which learn strategies from visual inputs via reinforcement learning. Many existing multi-agent reinforcement learning (MARL) algorithms however don't scale to environments where agents operate on visual inputs. To address this issue, algorithmically, recent works have focused on non-stationarity and exploration. In contrast, we study whether scalability can also be achieved via a disentangled representation. For this, we explicitly construct an objectcentric intermediate representation to characterize the states of an environment, which we refer to as 'semantic tracklets.' We evaluate 'semantic tracklets' on the visual multi-agent particle environment (VMPE) and on the challenging visual multiagent GFootball environment. 'Semantic tracklets' consistently outperform baselines on VMPE, and achieve a +2.4 higher score difference than baselines on GFootball. Notably, this method is the first to successfully learn a strategy for five players in the GFootball environment using only visual data. For more, please see our project page: https://ioujenliu.github. io/SemanticTracklets

show abstract

“…6) Cordial Sync [24]: We utilize the structure of the decision policy proposed in [24], which is a decentralized model without scene prior knowledge, and modify it to apply to multi-agent navigation.…”

Section: Baselinesmentioning

confidence: 99%

“…Communication mechanism has also been studied [22] and applicated in a navigation task in which all agents need to find one same target through communication. FurnLift [23] and FurnMove [24] tasks are newly proposed to study multi-agent cooperation in embodied tasks. However, the proposed approaches for FurnLift and FurnMove mainly tackle the circumstances that two agents work together to complete a single task.…”

Section: Introductionmentioning

confidence: 99%

Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge

Xin-zhu¹,

Guo²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

In visual semantic navigation, the robot navigates to a target object with egocentric visual observations and the class label of the target is given. It is a meaningful task inspiring a surge of relevant research. However, most of the existing models are only effective for single-agent navigation, and a single agent has low efficiency and poor fault tolerance when completing more complicated tasks. Multi-agent collaboration can improve the efficiency and has strong application potentials. In this paper, we propose the multi-agent visual semantic navigation, in which multiple agents collaborate with others to find multiple target objects. It is a challenging task that requires agents to learn reasonable collaboration strategies to perform efficient exploration under the restrictions of communication bandwidth. We develop a hierarchical decision framework based on semantic mapping, scene prior knowledge, and communication mechanism to solve this task. The results of testing experiments in unseen scenes with both known objects and unknown objects illustrate the higher accuracy and efficiency of the proposed model compared with the single-agent model.

show abstract

A Cordial Sync: Going Beyond Marginal Policies for Multi-agent Embodied Tasks

Cited by 37 publications

References 72 publications

The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation

The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation

Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning

Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge

Contact Info

Product

Resources

About