Vision‐based Obstacle Detection and Navigation for an Agricultural Robot

Ball, David; Upcroft, Ben; Wyeth, Gordon; Corke, Peter; English, Andrew; Ross, Patrick; Patten, Timothy; Fitch, Robert; Sukkarieh, Salah; Bate, Andrew

doi:10.1002/rob.21644

Cited by 112 publications

(58 citation statements)

References 56 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Since then, several systems have been proposed for detecting and avoiding obstacles (Cho and Lee, 2000;Stentz et al, 2002;Griepentrog et al, 2009;Moorehead et al, 2012;Emmi et al, 2014;Ball et al, 2016).…”

Section: Related Workmentioning

confidence: 99%

Multi-Modal Detection and Mapping of Static and Dynamic Obstacles in Agriculture for Process Evaluation

et al. 2018

View full text Add to dashboard Cite

Today, agricultural vehicles are available that can automatically perform tasks such as weed detection and spraying, mowing, and sowing while being steered automatically. However, for such systems to be fully autonomous and self-driven, not only their specific agricultural tasks must be automated. An accurate and robust perception system automatically detecting and avoiding all obstacles must also be realized to ensure safety of humans, animals, and other surroundings. In this paper, we present a multi-modal obstacle and environment detection and recognition approach for process evaluation in agricultural fields. The proposed pipeline detects and maps static and dynamic obstacles globally, while providing process-relevant information along the traversed trajectory. Detection algorithms are introduced for a variety of sensor technologies, including range sensors (lidar and radar) and cameras (stereo and thermal). Detection information is mapped globally into semantical occupancy grid maps and fused across all sensors with late fusion, resulting in accurate traversability assessment and semantical mapping of process-relevant categories (e.g., crop, ground, and obstacles). Finally, a decoding step uses a Hidden Markov model to extract relevant process-specific parameters along the trajectory of the vehicle, thus informing a potential control system of unexpected structures in the planned path. The method is evaluated on a public dataset for multimodal obstacle detection in agricultural fields. Results show that a combination of multiple sensor modalities increases detection performance and that different fusion strategies must be applied between algorithms detecting similar and dissimilar classes.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-Modal Detection and Mapping of Static and Dynamic Obstacles in Agriculture for Process Evaluation

et al. 2018

View full text Add to dashboard Cite

show abstract

“…RTK GPS receivers are attractive because of their high accuracy, repeatability, and availability. However, their size, weight, reliability, and cost make them unattractive for use on micro‐UAVs (Ball et al., ). Even short‐term GPS coverage loss, caused by trees, hills, or surrounding structures, will cause vehicles to significantly drift from their target paths (Roth & Singh, ).…”

Section: Related Workmentioning

confidence: 99%

UAV Localization in Row Crops

Anthony

Detweiler

2017

Journal of Field Robotics

View full text Add to dashboard Cite

High‐flying unmanned aerial vehicles (UAVs) are transforming industrial and research agriculture by delivering high spatiotemporal resolution data on a field environment. While current UAVs fly high above fields collecting aerial imagery, future low‐flying aircraft will directly interact with the environment and will utilize a wider variety of sensors. Safely and reliably operating close to unstructured environments requires improving UAVs' sensing, localization, and control algorithms. To this end, we investigate localizing a micro‐UAV in corn phenotyping trials using a laser scanner and IMU to control the altitude and position of the vehicle relative to the plant rows. In this process, the laser scanner is not only a means of localization, but also a scientific instrument for measuring plant properties. Experimental evaluations demonstrate that the is capable of safely and reliably operating in real‐world phenotyping trials. We experimentally validate the system in both low and high wind conditions in fully mature corn fields. Using test data from 18 test flights, we show that the UAV is capable of localizing its position to within one field row of the true position.

show abstract

“…The most affordable sensor for direct measurement of position, GNSS, does not reach this level of accuracy [8]. Furthermore, GNSS suffers from occasional outages in position due to communication link failures and loss of satellite lock due to occlusion by obstacles such as trees [9,10]. LASER scanners (LIDAR), or laser rangefinders, are commonly employed to obtain three-dimensional point clouds of the area for off-road navigation [11], for urban search and rescue, or for agricultural applications [12,13].…”

Section: Introductionmentioning

confidence: 99%

3D Autonomous Navigation Line Extraction for Field Roads Based on Binocular Vision

Wang

Liu³

2019

Journal of Sensors

View full text Add to dashboard Cite

This paper proposes a 3D autonomous navigation line extraction method for field roads in hilly regions based on a low-cost binocular vision system. Accurate guide path detection of field roads is a prerequisite for the automatic driving of agricultural machines. First, considering the lack of lane lines, blurred boundaries, and complex surroundings of field roads in hilly regions, a modified image processing method was established to strengthen shadow identification and information fusion to better distinguish the road area from its surroundings. Second, based on nonobvious shape characteristics and small differences in the gray values of the field roads inside the image, the centroid points of the road area as its statistical feature was extracted and smoothed and then used as the geometric primitives of stereo matching. Finally, an epipolar constraint and a homography matrix were applied for accurate matching and 3D reconstruction to obtain the autonomous navigation line of the field roads. Experiments on the automatic driving of a carrier on field roads showed that on straight roads, multicurvature complex roads and undulating roads, the mean deviations between the actual midline of the road and the automatically traveled trajectory were 0.031 m, 0.069 m, and 0.105 m, respectively, with maximum deviations of 0.133, 0.195 m, and 0.216 m, respectively. These test results demonstrate that the proposed method is feasible for road identification and 3D navigation line acquisition.

show abstract

Vision‐based Obstacle Detection and Navigation for an Agricultural Robot

Cited by 112 publications

References 56 publications

Multi-Modal Detection and Mapping of Static and Dynamic Obstacles in Agriculture for Process Evaluation

Multi-Modal Detection and Mapping of Static and Dynamic Obstacles in Agriculture for Process Evaluation

UAV Localization in Row Crops

3D Autonomous Navigation Line Extraction for Field Roads Based on Binocular Vision

Contact Info

Product

Resources

About