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

Abstract

Artificial perception for robots operating in outdoor natural environments, including forest scenarios, has been the object of a substantial amount of research for decades. Regardless, this has proven to be one of the most difficult research areas in robotics and has yet to be robustly solved. This happens namely due to difficulties in dealing with environmental conditions (trees and relief, weather conditions, dust, smoke, etc.), the visual homogeneity of natural landscapes as opposed to the diversity of natural obstacles to be avoided, and the effect of vibrations or external forces such as wind, among other technical challenges. Consequently, we propose a new survey, describing the current state of the art in artificial perception and sensing for robots in precision forestry. Our goal is to provide a detailed literature review of the past few decades of active research in this field. With this review, we attempted to provide valuable insights into the current scientific outlook and identify necessary advancements in the area. We have found that the introduction of robotics in precision forestry imposes very significant scientific and technological problems in artificial sensing and perception, making this a particularly challenging field with an impact on economics, society, technology, and standards. Based on this analysis, we put forward a roadmap to address the outstanding challenges in its respective scientific and technological landscape, namely the lack of training data for perception models, open software frameworks, robust solutions for multi-robot teams, end-user involvement, use case scenarios, computational resource planning, management solutions to satisfy real-time operation constraints, and systematic field testing. We argue that following this roadmap will allow for robotics in precision forestry to fulfil its considerable potential.

Sensors for Digital Transformation in Smart Forestry

“…A recent study evaluated how different perception technologies are used in conjunction with robots today. A major downside identified in this study was the non-existence of robot teams within forestry [95].…”

A LiDAR-Camera-Inertial-GNSS Apparatus for 3D Multimodal Dataset Collection in Woodland Scenarios

“…To complement the LiDAR data, the Mynt Eye provides point clouds with a larger horizontal FoV of 146 • . The Intel Realsense D435i camera not only provides additional depth information but also serves as the single source of RGB and infrared information, which is useful for identifying relevant forest entities, such as flammable material [3]. The system also contains an onboard computer, the Udoo Bolt V3, that is responsible for receiving and recording data from every sensor.…”

“…Forest areas are characterized by various obstacles, such as dense vegetation, uneven terrains, and dynamic changes due to growth and decay. Conventional forestry robots may struggle to maneuver through these challenging conditions, leading to limited coverage and incomplete data acquisition [3]. The lack of flexibility in conventional forestry robots also hampers their ability to access hard-to-reach areas.…”

Power Consumption Analysis of a Prototype Lightweight Autonomous Electric Cargo Robot in Agricultural Field Operation Scenarios

“…Despite the aforementioned benefits of investigating the power characteristics of the electric agricultural robots, little progress has been made toward this direction and priority shifting is required. Indeed, numerous studies are directed towards the potential of enhancing the intelligence of robotic vehicles to perform agricultural operations, mainly focusing on (or improving) a single characteristic [43,44]. The examination of literature reviews dedicated to agricultural robotic vehicles [12,27,[43][44][45] reflects the focus of the researchers on improving the intelligence of robots, but it also verifies that only a limited number of works address the energy performance assessment of the robotic platforms [46][47][48].…”

“…Indeed, numerous studies are directed towards the potential of enhancing the intelligence of robotic vehicles to perform agricultural operations, mainly focusing on (or improving) a single characteristic [43,44]. The examination of literature reviews dedicated to agricultural robotic vehicles [12,27,[43][44][45] reflects the focus of the researchers on improving the intelligence of robots, but it also verifies that only a limited number of works address the energy performance assessment of the robotic platforms [46][47][48]. The existing scientific landscape indicates that, for the moment, researchers place more emphasis on immediate concerns and challenges, such as functionality and accuracy, rather than delving into the complexities of energy-related aspects, as agricultural robotics, especially in the context of electric vehicles, is still in its nascent stages.…”