Abstract:There is a growing interest in new sensing technologies and processing algorithms to increase the level of driving automation towards self-driving vehicles. The challenge for autonomy is especially difficult for the negotiation of uncharted scenarios, including natural terrain. This paper proposes a method for terrain unevenness estimation that is based on the power spectral density (PSD) of the surface profile as measured by exteroceptive sensing, that is, by using a common onboard range sensor such as a ster… Show more
“…In the experimental part, a grid resolution of 0.2 ร 0.2 m has been considered. Assuming that the cells of the grid map are independent from each other, and given a series of rock observations ๐ง 1:๐ , the probability belief of a single cell to be occupied by an obstacle or not ๐(๐ ๐ฅ,๐ฆ |๐ง 1:๐ ), is reported in Equation (4).…”
Section: Sensor Fusionmentioning
confidence: 99%
“…This system was able to detect geometric hazards such as rock, ditches, and cliffs by processing the 3D point clouds generated by the rover stereoimages; it looked mainly at geometric characteristics such as steps, slopes, and terrain roughness. An alternative method for estimating the traversability of a terrain is presented in [4], where the unevenness of the terrain is analysed by means of the power spectral density (PSD) of the surface profile as measured by a stereo camera. In [5] an evaluation system for the traversability of rough terrain for a rover based on aerial UAV survey is presented.…”
Obstacle mapping is a fundamental building block of the autonomous navigation pipeline of many robotic platforms such as planetary rovers. Nowadays, occupancy grid mapping is a widely used tool for obstacle perception. It foreseen the representation of the environment in evenly spaced cells, whose posterior probability of being occupied is updated based on range sensors measurement. In more classic approaches, the cells are updated to occupied at the point where the ray emitted by the range sensor encounters an obstacle, such as a wall. The main limitation of this kind of methods is that they are not able to identify planar obstacles, such as slippery, sandy, or rocky soils. In this work, we use the measurements of a stereo camera combined with a pixel labeling technique based on Convolution Neural Networks to identify the presence of rocky obstacles in planetary environment. Once identified, the obstacles are converted into a scan-like model. The estimation of the relative pose between successive frames is carried out using ORB-SLAM algorithm. The final step consists of updating the occupancy grid map using the Bayesโ update Rule. To evaluate the metrological performances of the proposed method images from the Martian analogous dataset, the ESA Katwijk Beach Planetary Rover Dataset have been used. The evaluation has been performed by comparing the generated occupancy map with a manually segmented ortomosaic map, obtained by dronesโ survey of the area used as reference.
“…In the experimental part, a grid resolution of 0.2 ร 0.2 m has been considered. Assuming that the cells of the grid map are independent from each other, and given a series of rock observations ๐ง 1:๐ , the probability belief of a single cell to be occupied by an obstacle or not ๐(๐ ๐ฅ,๐ฆ |๐ง 1:๐ ), is reported in Equation (4).…”
Section: Sensor Fusionmentioning
confidence: 99%
“…This system was able to detect geometric hazards such as rock, ditches, and cliffs by processing the 3D point clouds generated by the rover stereoimages; it looked mainly at geometric characteristics such as steps, slopes, and terrain roughness. An alternative method for estimating the traversability of a terrain is presented in [4], where the unevenness of the terrain is analysed by means of the power spectral density (PSD) of the surface profile as measured by a stereo camera. In [5] an evaluation system for the traversability of rough terrain for a rover based on aerial UAV survey is presented.…”
Obstacle mapping is a fundamental building block of the autonomous navigation pipeline of many robotic platforms such as planetary rovers. Nowadays, occupancy grid mapping is a widely used tool for obstacle perception. It foreseen the representation of the environment in evenly spaced cells, whose posterior probability of being occupied is updated based on range sensors measurement. In more classic approaches, the cells are updated to occupied at the point where the ray emitted by the range sensor encounters an obstacle, such as a wall. The main limitation of this kind of methods is that they are not able to identify planar obstacles, such as slippery, sandy, or rocky soils. In this work, we use the measurements of a stereo camera combined with a pixel labeling technique based on Convolution Neural Networks to identify the presence of rocky obstacles in planetary environment. Once identified, the obstacles are converted into a scan-like model. The estimation of the relative pose between successive frames is carried out using ORB-SLAM algorithm. The final step consists of updating the occupancy grid map using the Bayesโ update Rule. To evaluate the metrological performances of the proposed method images from the Martian analogous dataset, the ESA Katwijk Beach Planetary Rover Dataset have been used. The evaluation has been performed by comparing the generated occupancy map with a manually segmented ortomosaic map, obtained by dronesโ survey of the area used as reference.
“…It should be noted that the proposed approach assumes the availability of a sensing strategy to measure the degree of terrain irregularity in front of the vehicle. This task can be achieved using exteroceptive sensing with a Lidar (Fernandez-Diaz, 2010) or stereovision (Reina et al, 2019). Figure 2.Block diagram of the proposed approach for state/parameter estimation running in parallel to the system.…”
The extent of vibrations experienced by a vehicle driving over natural terrain defines its ride quality. Generally, surface irregularities, ranging from single discontinuities to random variations of the elevation profile, act as a major source of excitation that induces vibrations in the vehicle body through the tire-soil interaction and suspension system. Therefore, the ride response of off-road-vehicles is tightly connected with the ground properties. The objective of this research is to develop a model-based observer that estimates automatically terrain parameters using available onboard sensors. Two acceleration signals, one coming from the vehicle body and one from the wheel suspension are fed into a dynamic vehicle model that takes into account tire/terrain interaction to estimate ground properties. To solve the resulting nonlinear simultaneous state and parameter estimation problem, the Cubature Kalman filter is used that is shown to outperform the standard Extended Kalman filter in terms of accuracy and stability. An extensive set of simulation tests is presented to assess the performance of the proposed estimator under various surface roughness and deformability conditions. Results show the potential of the proposed observer to estimate automatically terrain properties during operations that could be implemented onboard of a general family of intelligent vehicles, ranging from off-road high-speed passenger cars to lightweight and low-speed planetary rovers. Prepared using sagej.cls arXiv:2001.05165v1 [eess.SY] 15 Jan 2020
“…Furthermore, in plain conditions on rougher soil surfaces, rainfall events mobilize soil aggregates, reducing relative roughness, indirectly promoting the phenomenon of raindrop splashing, thus forming crust and sealing the soil [12]. Since the SSR characterizes the shape of any soil surface, they also play a critical role for agricultural vehicle navigation, because they directly affect the dynamic response in terms of vertical vibrations, responsible for human comfort and handling performance, traction and safety, including extreme cases of vehicle entrapment or rollover [13]. Furthermore, new generations of agricultural vehicles [14] need to be sensitive to the SSR in order to achieve an advanced level of autonomous navigation, namely the optimal path planning in terms of traction, travel velocity and safety with less or no human supervision [15,16], that represents an important challenge for the Agriculture 4.0 [17,18].…”
Section: Introductionmentioning
confidence: 99%
“…Stereo and depth cameras represent a good trade-off between strengths and weaknesses of the various systems available nowadays. As a matter of fact, they ensure dense 3D reconstruction at short/medium range with reasonable accuracy, being at the same time more affordable than other systems [13,25,27,28]. It should be also underlined that RGB-D devices lend themselves very well to integration on intelligent robot farmers for high throughput in-field monitoring, leveraging on their compactness and lightness.…”
Agricultural soils provide a variety of ecological services, including nutrient cycling, water purification and storage, carbon sequestration, and flood protection. Soil Surface Roughness (SSR) represents a key parameter for evaluating the terrain quality structure, especially in the layers beneath the usual primary tillage depth, and therefore its estimation has been widely investigated over the years in many fields of science and engineering. This paper proposes the adoption of an innovative sensing approach that relies on contactless measurements provided by a depth camera in contrast to traditional contact measurements such as pin meter and roller chain. In addition, novel features are investigated to achieve a complete statistical description of the SSR with the least number of parameters. The proposed methods are validated in an experimental campaign performed on a vineyard plot. This research could be useful for many applications, including soil erosion prediction models, autonomous vehicle navigation in rural and agricultural settings, and controlled traffic farming.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citationsโcitations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
