Exploiting Reusable Paths in Mobile Robotics: Benefits and Challenges for Long-term Autonomy

Barfoot, Timothy D.; Stenning, Braden; Furgale, Paul; McManus, Colin

doi:10.1109/crv.2012.58

Cited by 9 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, with the visual‐teach‐and‐repeat system considered, this failure is rare [<0.4% of distance traveled, and if the requirement is that the robot be able to travel in at least one direction, the failure rate is even lower (Furgale and Barfoot, )] so the simplification is justified at this stage. There are typically two ways that this assumption is broken (Barfoot et al., ): The appearance of the scene changes such that the system cannot localize against the map. The path cannot be reversed (for example after sliding down a steep hill or going down a high step, though in these cases the path is still likely repeatable in the same direction), or the traversability of the path changes so that it is no longer traversable (e.g., the path becomes blocked). …”

Section: Using a Network Of Reusable Pathsmentioning

confidence: 99%

“…The stereo‐camera‐equipped robot was limited to operating in similar lighting conditions throughout a test, because a change in the lighting conditions changed the appearance of the scene and made localizing against the map difficult or impossible. To solve this problem, a lighting‐invariant system was created that makes use of a high‐framerate lidar (Barfoot et al., ; McManus et al., , ). Field test results from this system are presented next.…”

Section: Field Testsmentioning

confidence: 99%

“…A lighting‐invariant extension to this work, using a high‐framerate lidar (McManus et al., , ), has been developed to address one of the major challenges of the stereo‐camera‐based system (Barfoot et al., ), namely, appearance changes due to changing lighting conditions can make it challenging, or impossible, to localize against the map when revisiting places. This system allows for operation in complete darkness, making it suitable for exploration of permanently shadowed regions such as those at the Lunar South Pole.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Planning using a Network of Reusable Paths: A Physical Embodiment of a Rapidly Exploring Random Tree

Stenning

McManus

Barfoot

2013

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

Growing a network of reusable paths is a novel approach to navigation that allows a mobile robot to autonomously seek distant goals in unmapped, GPS‐denied environments, which may make it particularly well‐suited to rovers used for planetary exploration. A network of reusable paths is an extension to visual‐teach‐and‐repeat systems; instead of a simple chain of poses, there is an arbitrary network. This allows the robot to return to any pose it has previously visited, and it lets a robot plan to reuse previous paths. This paradigm results in closer goal acquisition (through reduced localization error) and a more robust approach to exploration with a mobile robot. It also allows a rover to return a sample to an ascent vehicle with a single command. We show that our network‐of‐reusable‐paths approach is a physical embodiment of the popular rapidly exploring random tree (RRT) planner. Simulation results are presented along with the results from two different robotic test systems. These test systems drove over 14 km in planetary analog environments.

show abstract

Section: Using a Network Of Reusable Pathsmentioning

confidence: 99%

Section: Field Testsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Planning using a Network of Reusable Paths: A Physical Embodiment of a Rapidly Exploring Random Tree

Stenning

McManus

Barfoot

2013

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

show abstract

“…In many mobile robot applications, it is adequate if not necessary, to explore and navigate the environment by creating and maintaining a network of paths analogous to migration routes or automobile roads [1]. The use and reuse of paths reduces the need for repeated application of exploratory and terrain assessing software and also provides an opportunity for learning behavior.…”

Section: Introductionmentioning

confidence: 99%

Visual teach and repeat, repeat, repeat: Iterative Learning Control to improve mobile robot path tracking in challenging outdoor environments

Ostafew

Schoellig

Barfoot

2013

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

This paper presents a path-repeating, mobile robot controller that combines a feedforward, proportional Iterative Learning Control (ILC) algorithm with a feedback-linearized path-tracking controller to reduce path-tracking errors over repeated traverses along a reference path. Localization for the controller is provided by an on-board, vision-based mapping and navigation system enabling operation in large-scale, GPSdenied, extreme environments. The paper presents experimental results including over 600 m of travel by a four-wheeled, 50 kg robot travelling through challenging terrain including steep hills and sandy turns and by a six-wheeled, 160 kg robot at gradually-increased speeds up to three times faster than the nominal, safe speed. In the absence of a global localization system, ILC is demonstrated to reduce path-tracking errors caused by unmodelled robot dynamics and terrain challenges.

show abstract

“…They could provide solution fast and without the usage of a lot of computing power. Usability of RRT-based solutions for long-term autonomy problems in complex environments is shown in [2]. In [3] authors used RRT* for local path planning during mine exploration.…”

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of RRT-Based Methods for Pathfinding in Underground Environment

Protsenko

Ivanov

2020

A.I.S.

View full text Add to dashboard Cite

Ab s t r a c t. The importance of finding a path for autonomous moving robots is indispensable, because the successful achievement of the target location depends on the solution of this problem. There are a large number of different methods of finding the way, which differ in the accuracy of work, speed, the need for additional equipment. Underground environments, such as mines and tunnels, differ from other structures and open space, and therefore, require different approach when performing pathfinding, as narrow, curved passages and heterogeneous structure could render some of the pathfinding methods ineffective. However, methods based on rapidly exploring random trees (RRT) maintain their effectiveness because they are unaffected by the complexity of the environment. In this article presented a comparison of the three RRT-based methods: RRT, RRT-connect and RRT*. K e ywor d s : robot; pathfinding; autonomy; RRT.

show abstract

Exploiting Reusable Paths in Mobile Robotics: Benefits and Challenges for Long-term Autonomy

Cited by 9 publications

References 24 publications

Planning using a Network of Reusable Paths: A Physical Embodiment of a Rapidly Exploring Random Tree

Planning using a Network of Reusable Paths: A Physical Embodiment of a Rapidly Exploring Random Tree

Visual teach and repeat, repeat, repeat: Iterative Learning Control to improve mobile robot path tracking in challenging outdoor environments

Comparative Analysis of RRT-Based Methods for Pathfinding in Underground Environment

Contact Info

Product

Resources

About