Traversability analysis with vision and terrain probing for safe legged robot navigation

Haddeler, Garen; Chuah, Meng Yee; You, Yangwei; Chan, Jianle; Adiwahono, Albertus Hendrawan; Yau, Wei-Yun; Chew, Chee-Meng

doi:10.3389/frobt.2022.887910

Cited by 5 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More principled approaches such as Gaussian process models and Bayesian deep neural networks appear promising, but computationally expensive, to infer the uncertainty in steering directions, and consequently plan safe paths for the rover (e.g., [66,67]). Finally, hardware or behaviorbased solutions (e.g., see [68,69]), to nudge and probe obstacles such as grass and dense bushes, may be integrated onto the rover platform to actively reduce the uncertainty in scene understanding.…”

Section: Discussionmentioning

confidence: 99%

End-to-End Learning for Visual Navigation of Forest Environments

Niu

Zauner

Tarapore

2023

Forests

View full text Add to dashboard Cite

Off-road navigation in forest environments is a challenging problem in field robotics. Rovers are required to infer their traversability over a priori unknown and dynamically changing forest terrain using noisy onboard navigation sensors. The problem is compounded for small-sized rovers, such as that of a swarm. Their size-proportional low-viewpoint affords them a restricted view for navigation, which may be partially occluded by forest vegetation. Hand-crafted features, typically employed for terrain traversability analysis, are often brittle and may fail to discriminate obstacles in varying lighting and weather conditions. We design a low-cost navigation system tailored for small-sized forest rovers using self-learned features. The MobileNet-V1 and MobileNet-V2 models, trained following an end-to-end learning approach, are deployed to steer a mobile platform, with a human-in-the-loop, towards traversable paths while avoiding obstacles. Receiving a 128 × 96 pixel RGB image from a monocular camera as input, the algorithm running on a Raspberry Pi 4, exhibited robustness to motion blur, low lighting, shadows and high-contrast lighting conditions. It was able to successfully navigate a total of over 3 km of real-world forest terrain comprising shrubs, dense bushes, tall grass, fallen branches, fallen tree trunks, and standing trees, in over five different weather conditions and four different times of day.

show abstract

Section: Discussionmentioning

confidence: 99%

End-to-End Learning for Visual Navigation of Forest Environments

Niu

Zauner

Tarapore

2023

Forests

View full text Add to dashboard Cite

show abstract

An embarrassingly simple approach for visual navigation of forest environments

et al. 2023

View full text Add to dashboard Cite

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.

show abstract

Terrain-aware semantic mapping for cooperative subterranean exploration

Miles,

Biggie,

Heckman

2023

Front. Robot. AI

View full text Add to dashboard Cite

Navigation over torturous terrain such as those in natural subterranean environments presents a significant challenge to field robots. The diversity of hazards, from large boulders to muddy or even partially submerged Earth, eludes complete definition. The challenge is amplified if the presence and nature of these hazards must be shared among multiple agents that are operating in the same space. Furthermore, highly efficient mapping and robust navigation solutions are absolutely critical to operations such as semi-autonomous search and rescue. We propose an efficient and modular framework for semantic grid mapping of subterranean environments. Our approach encodes occupancy and traversability information, as well as the presence of stairways, into a grid map that is distributed amongst a robot fleet despite bandwidth constraints. We demonstrate that the mapping method enables safe and enduring exploration of subterranean environments. The performance of the system is showcased in high-fidelity simulations, physical experiments, and Team MARBLE’s entry in the DARPA Subterranean Challenge which received third place.

show abstract

Traversability analysis with vision and terrain probing for safe legged robot navigation

Cited by 5 publications

References 33 publications

End-to-End Learning for Visual Navigation of Forest Environments

End-to-End Learning for Visual Navigation of Forest Environments

An embarrassingly simple approach for visual navigation of forest environments

Terrain-aware semantic mapping for cooperative subterranean exploration

Contact Info

Product

Resources

About