Kilometer-scale autonomous navigation in subarctic forests: challenges and lessons learned

Abstract

Challenges inherent to autonomous wintertime navigation in forests include lack of a reliable Global Navigation Satellite System (GNSS) signal, low feature contrast, high illumination variations, and changing environment. This type of off-road environment is an extreme case of situations autonomous cars could encounter in northern regions. Thus, it is important to understand the impact of this harsh environment on autonomous navigation systems. To this end, we present a field report analyzing teach-and-repeat navigation in a subarctic forest while subject to fluctuating weather, including light and heavy snow, rain, and drizzle. First, we describe the system, which relies on point cloud registration to localize a mobile robot through a boreal forest, while simultaneously building a map. We experimentally evaluate this system in over 18.8km of autonomous navigation in the teach-and-repeat mode. Over 14 repeat runs, only four manual interventions were required, three of which were due to localization failure and another one caused by battery power outage. We show that dense vegetation perturbs the GNSS signal, rendering it unsuitable for navigation in forest trails. Furthermore, we highlight the increased uncertainty related to localizing using point cloud registration in forest trails. We demonstrate that it is not snow precipitation, but snow accumulation, that affects our system’s ability to localize within the environment. Finally, we expose some challenges and lessons learned from our field campaign to support better experimental work in winter conditions. Our dataset is available online.

Sensing and Artificial Perception for Robots in Precision Forestry: A Survey

“…The Northern Robotics Laboratory (NOR) at Laval University in Canada is a research group that specializes in mobile and autonomous systems in harsh outdoor conditions (see project SNOW [88]). Relevant research work includes SLAM in forest environments [89,90] and autonomous navigation in subarctic forests [91]. The Massachusetts Institute of Technology, namely through the Robotic Mobility Group, has produced work on robotic perception for forested environments.…”

Along Similar Lines: Local Obstacle Avoidance for Long-Term Autonomous Path Following

“…The emergence of 3D LiDAR-based VT&R architectures [4], [5], [8], [9] with improved localization robustness up to several meters away from the path has made local obstacle avoidance more feasible. Krusi et al [5] utilized the additional mobility freedom to navigate reliably in dynamic environments.…”

“…Instead, we can rely on another observation: these regions are closely linked to the curvature of the reference path, specifically the instantaneous Radius of Curvature (ROC). Our key insight is to notice that all points where q > ROC also satisfy the equality in equation (8). Although the ROC does not fully describe the singularity regions, it provides a promising starting point for our search.…”

An embarrassingly simple approach for visual navigation of forest environments

“…The existing approaches to off-road navigation appear unsuitable for inexpensive small-sized forest rovers . Large-sized rovers, typically used in studies for off-road navigation, perceive the environment from a high viewpoint of around 1 m (e.g., Ho et al (2013a ; b) ; Ugenti et al (2022) ; Fnadi et al (2020) ; Baril et al (2022) ; Bagnell et al (2010) , also see comparison in Table 1 and Figure 1A ). In comparison, for small-sized forest rovers, discerning the forest scene from a size-proportional low viewpoint on the order of centimeters is relatively difficult due to the limited field-of-view in the vertical direction.…”