Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles

Manderson, Travis; Higuera, Juan Camilo Gamboa; Wapnick, Stefan; Tremblay, Jean‐François; Shkurti, Florian; Meger, David; Dudek, Gregory

doi:10.15607/rss.2020.xvi.048

Cited by 37 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A planner was used to help the robot traverse through tall grass and reach a goal deemed as untraversable, using classic SLAM in conjunction with planning. A data-efficient end-to-end learning method for goal-conditioned visual navigation was proposed (Manderson et al, 2020). They applied their system to underwater autonomous vehicles navigating through a coral-rich area to collect relevant data while avoiding collisions.…”

Section: Sim-to-real Deep Reinforcement Learningmentioning

confidence: 99%

A Heterogeneous Unmanned Ground Vehicle and Blimp Robot Team for Search and Rescue using Data-driven Autonomy and Communication-aware Navigation

Lu¹,

Huang²,

Huang³

et al. 2022

View full text Add to dashboard Cite

This paper describes the architecture and implementation of a heterogeneous team comprising unmanned ground vehicles and blimp robots capable of navigating unknown subter- ranean environments for search and rescue missions. The ground vehicles are equipped with a range of sensors for accurate perception, localization, and mapping. The blimps feature a long flight duration and collision tolerance when traversing uneven terrain. The design of the system was meant to satisfy the requirements of the Defense Advanced Research Projects Agency (DARPA) Subterranean Challenge in terms of perception capability and autonomy. To facilitate navigation through smoke-filled spaces, we employed novel millimeter wave radar to enable cross-modal representations for integration via deep reinforcement learning. The autonomy of the proposed scheme was augmented using simulations to train deep neural networks, thereby allowing the system to perform sequential decision-making for collision avoidance and navigation toward a specific goal. The navigation system was evaluated in the DARPA SubT Urban Circuit, and quantitative localization results and recovery strategy from failures was discussed. The proposed communication system comprises mesh WiFi with XBee (ZigBee network with XBee radios) and ultra-wideband (UWB) communication modules as well as spherical nodes that can be shot out like a cannonball and miniature cars deployed as mobile nodes. The propagation and radio signal strength index of various modules were evaluated using data collected during field tests in order to overcome the uncertainties of subterranean environments, including non-line-of-sight propagation, multipath propagation, and fading reception. We also discuss the lessons learned during this project and reflect on future plans.

show abstract

Section: Sim-to-real Deep Reinforcement Learningmentioning

confidence: 99%

A Heterogeneous Unmanned Ground Vehicle and Blimp Robot Team for Search and Rescue using Data-driven Autonomy and Communication-aware Navigation

Lu¹,

Huang²,

Huang³

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Finally, on the front of perception-aware underwater navigation, Manderson et al [41] provided an extension to their previous work. Similarly to [39], this deep-learning technique was based on fitting on data collected by a human operator controlling the robot.…”

Section: Related Workmentioning

confidence: 99%

AquaVis: A Perception-Aware Autonomous Navigation Framework for Underwater Vehicles

Xanthidis¹,

Kalaitzakis²,

Karapetyan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Visual monitoring operations underwater require both observing the objects of interest in close-proximity, and tracking the few feature-rich areas necessary for state estimation. This paper introduces the first navigation framework, called AquaVis, that produces on-line visibility-aware motion plans that enable Autonomous Underwater Vehicles (AUVs) to track multiple visual objectives with an arbitrary camera configuration in real-time. Using the proposed pipeline, AUVs can efficiently move in 3D, reach their goals while avoiding obstacles safely, and maximizing the visibility of multiple objectives along the path within a specified proximity. The method is sufficiently fast to be executed in real-time and is suitable for single or multiple camera configurations. Experimental results show the significant improvement on tracking multiple automaticallyextracted points of interest, with low computational overhead and fast re-planning times.Accompanying short video: https://youtu.be/JKO bbrIZyU

show abstract

“…Multi-robot teams are a viable solution for a variety of applications that involve distributed or simultaneous tasks, such as disaster response [1], area exploration [2], and search and rescue [3]. To effectively address such applications, robots must be able to move through complex environments and arrive at waypoints and goal positions [4]. While planning its own navigation actions, each robot must avoid obstacles as well as collisions with its teammates who are making their own movements.…”

Section: Introductionmentioning

confidence: 99%

Decentralized and Communication-Free Multi-Robot Navigation through Distributed Games

Reily,

Mott,

Zhang

2020

Preprint

View full text Add to dashboard Cite

Effective multi-robot teams require the ability to move to goals in complex environments in order to address real-world applications such as search and rescue. Multi-robot teams should be able to operate in a completely decentralized manner, with individual robot team members being capable of acting without explicit communication between neighbors. In this paper, we propose a novel game theoretic model that enables decentralized and communication-free navigation to a goal position. Robots estimate the behavior of their local teammates in order to identify behaviors that move them in the direction of the goal, while also avoiding obstacles and maintaining team cohesion without collisions. We prove theoretically that generated actions approach a Nash equilibrium, which also corresponds to an optimal strategy identified for each robot. We show through simulations that our approach enables decentralized and communication-free navigation by a multi-robot system to a goal position, avoiding obstacles and collisions, while also maintaining connectivity.

show abstract

Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles

Cited by 37 publications

References 27 publications

A Heterogeneous Unmanned Ground Vehicle and Blimp Robot Team for Search and Rescue using Data-driven Autonomy and Communication-aware Navigation

A Heterogeneous Unmanned Ground Vehicle and Blimp Robot Team for Search and Rescue using Data-driven Autonomy and Communication-aware Navigation

AquaVis: A Perception-Aware Autonomous Navigation Framework for Underwater Vehicles

Decentralized and Communication-Free Multi-Robot Navigation through Distributed Games

Contact Info

Product

Resources

About