An embarrassingly simple approach for visual navigation of forest environments
Navigation in forest environments is a challenging and open problem in the area of field robotics. Rovers in forest environments are required to infer the traversability of a priori unknown terrains, comprising a number of different types of compliant and rigid obstacles, under varying lighting and...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Robotics and AI |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2023.1086798/full |
| _version_ | 1797793697508622336 |
|---|---|
| author | Chaoyue Niu Callum Newlands Klaus-Peter Zauner Danesh Tarapore |
| author_facet | Chaoyue Niu Callum Newlands Klaus-Peter Zauner Danesh Tarapore |
| author_sort | Chaoyue Niu |
| collection | DOAJ |
| description | Navigation in forest environments is a challenging and open problem in the area of field robotics. Rovers in forest environments are required to infer the traversability of a priori unknown terrains, comprising a number of different types of compliant and rigid obstacles, under varying lighting and weather conditions. The challenges are further compounded for inexpensive small-sized (portable) rovers. While such rovers may be useful for collaboratively monitoring large tracts of forests as a swarm, with low environmental impact, their small-size affords them only a low viewpoint of their proximal terrain. Moreover, their limited view may frequently be partially occluded by compliant obstacles in close proximity such as shrubs and tall grass. Perhaps, consequently, most studies on off-road navigation typically use large-sized rovers equipped with expensive exteroceptive navigation sensors. We design a low-cost navigation system tailored for small-sized forest rovers. For navigation, a light-weight convolution neural network is used to predict depth images from RGB input images from a low-viewpoint monocular camera. Subsequently, a simple coarse-grained navigation algorithm aggregates the predicted depth information to steer our mobile platform towards open traversable areas in the forest while avoiding obstacles. In this study, the steering commands output from our navigation algorithm direct an operator pushing the mobile platform. Our navigation algorithm has been extensively tested in high-fidelity forest simulations and in field trials. Using no more than a 16 × 16 pixel depth prediction image from a 32 × 32 pixel RGB image, our algorithm running on a Raspberry Pi was able to successfully navigate a total of over 750 m of real-world forest terrain comprising shrubs, dense bushes, tall grass, fallen branches, fallen tree trunks, small ditches and mounds, and standing trees, under five different weather conditions and four different times of day. Furthermore, our algorithm exhibits robustness to changes in the mobile platform’s camera pitch angle, motion blur, low lighting at dusk, and high-contrast lighting conditions. |
| first_indexed | 2024-03-13T02:51:01Z |
| format | Article |
| id | doaj.art-f0eb08c3ad6c4c0ebdf778bee39755bf |
| institution | Directory Open Access Journal |
| issn | 2296-9144 |
| language | English |
| last_indexed | 2024-03-13T02:51:01Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Robotics and AI |
| spelling | doaj.art-f0eb08c3ad6c4c0ebdf778bee39755bf2023-06-28T12:10:07ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442023-06-011010.3389/frobt.2023.10867981086798An embarrassingly simple approach for visual navigation of forest environmentsChaoyue NiuCallum NewlandsKlaus-Peter ZaunerDanesh TaraporeNavigation in forest environments is a challenging and open problem in the area of field robotics. Rovers in forest environments are required to infer the traversability of a priori unknown terrains, comprising a number of different types of compliant and rigid obstacles, under varying lighting and weather conditions. The challenges are further compounded for inexpensive small-sized (portable) rovers. While such rovers may be useful for collaboratively monitoring large tracts of forests as a swarm, with low environmental impact, their small-size affords them only a low viewpoint of their proximal terrain. Moreover, their limited view may frequently be partially occluded by compliant obstacles in close proximity such as shrubs and tall grass. Perhaps, consequently, most studies on off-road navigation typically use large-sized rovers equipped with expensive exteroceptive navigation sensors. We design a low-cost navigation system tailored for small-sized forest rovers. For navigation, a light-weight convolution neural network is used to predict depth images from RGB input images from a low-viewpoint monocular camera. Subsequently, a simple coarse-grained navigation algorithm aggregates the predicted depth information to steer our mobile platform towards open traversable areas in the forest while avoiding obstacles. In this study, the steering commands output from our navigation algorithm direct an operator pushing the mobile platform. Our navigation algorithm has been extensively tested in high-fidelity forest simulations and in field trials. Using no more than a 16 × 16 pixel depth prediction image from a 32 × 32 pixel RGB image, our algorithm running on a Raspberry Pi was able to successfully navigate a total of over 750 m of real-world forest terrain comprising shrubs, dense bushes, tall grass, fallen branches, fallen tree trunks, small ditches and mounds, and standing trees, under five different weather conditions and four different times of day. Furthermore, our algorithm exhibits robustness to changes in the mobile platform’s camera pitch angle, motion blur, low lighting at dusk, and high-contrast lighting conditions.https://www.frontiersin.org/articles/10.3389/frobt.2023.1086798/fulllow-viewpoint forest navigationlow-cost sensorssmall-sized roverssparse swarmsdepth predictioncompliant obstacles |
| spellingShingle | Chaoyue Niu Callum Newlands Klaus-Peter Zauner Danesh Tarapore An embarrassingly simple approach for visual navigation of forest environments Frontiers in Robotics and AI low-viewpoint forest navigation low-cost sensors small-sized rovers sparse swarms depth prediction compliant obstacles |
| title | An embarrassingly simple approach for visual navigation of forest environments |
| title_full | An embarrassingly simple approach for visual navigation of forest environments |
| title_fullStr | An embarrassingly simple approach for visual navigation of forest environments |
| title_full_unstemmed | An embarrassingly simple approach for visual navigation of forest environments |
| title_short | An embarrassingly simple approach for visual navigation of forest environments |
| title_sort | embarrassingly simple approach for visual navigation of forest environments |
| topic | low-viewpoint forest navigation low-cost sensors small-sized rovers sparse swarms depth prediction compliant obstacles |
| url | https://www.frontiersin.org/articles/10.3389/frobt.2023.1086798/full |
| work_keys_str_mv | AT chaoyueniu anembarrassinglysimpleapproachforvisualnavigationofforestenvironments AT callumnewlands anembarrassinglysimpleapproachforvisualnavigationofforestenvironments AT klauspeterzauner anembarrassinglysimpleapproachforvisualnavigationofforestenvironments AT daneshtarapore anembarrassinglysimpleapproachforvisualnavigationofforestenvironments AT chaoyueniu embarrassinglysimpleapproachforvisualnavigationofforestenvironments AT callumnewlands embarrassinglysimpleapproachforvisualnavigationofforestenvironments AT klauspeterzauner embarrassinglysimpleapproachforvisualnavigationofforestenvironments AT daneshtarapore embarrassinglysimpleapproachforvisualnavigationofforestenvironments |