LiDAR Based Negative Obstacle Detection for Field Autonomous Land Vehicles

Abstract

Negative obstacles for field autonomous land vehicles (ALVs) refer to ditches, pits, or terrain with a negative slope, which will bring risks to vehicles in travel. This paper presents a feature fusion based algorithm (FFA) for negative obstacle detection with LiDAR sensors. The main contributions of this paper are fourfold: (1) A novel three‐dimensional (3‐D) LiDAR setup is presented. With this setup, the blind area around the vehicle is greatly reduced, and the density of LiDAR data is greatly improved, which are critical for ALVs. (2) On the basis of the proposed setup, a mathematical model of the point distribution of a single scan line is deduced, which is used to generate ideal scan lines. (3) With the mathematical model, an adaptive matching filter based algorithm (AMFA) is presented to implement negative obstacle detection. Features of simulated obstacles in each scan line are employed to detect the real negative obstacles. They are supposed to match with features of the potential real obstacles. (4) Grounded on AMFA algorithm, a feature fusion based algorithm is proposed. FFA algorithm fuses all the features generated by different LiDARs or captured at different frames. Bayesian rule is adopted to estimate the weight of each feature. Experimental results show that the performance of the proposed algorithm is robust and stable. Compared with the state‐of‐the‐art techniques, the detection range is improved by 20%, and the computing time is reduced by an order of two magnitudes. The proposed algorithm had been successfully applied on two ALVs, which won the champion and the runner‐up in the “Overcome Danger 2014” ground unmanned vehicle challenge of China.

Autonomous vehicles: challenges, opportunities, and future implications for transportation policies

“…In order to acquire a 3D visualization of the environment, a set of Lidars is coupled and synchronized with rapidly rotating mirrors [102,103]. The main limitations of the Lidar system are their lack of coverage and range (unsuitable for long range or distance) and reflectivity issues.…”

Why is Internet of Autonomous Vehicles not as Plug and Play as We Think ? Lessons to Be Learnt From Present Internet and Future Directions

“…Efficient sensor development relying on ultrasonic technology [27], Radio Detection and Ranging (RADARs) [28], Light Detection and Ranging (LIDARs) [29]- [30] and complex image processing algorithms [4] as well as control systems and algorithms [31]- [32], have been developed. This enables the vehicles within the near field IAV, to announce and plan their trajectory in coordination with other cars [33]- [34] and coordinate their collective motion [28], [35]- [36] with other cars while traveling the form of platoons [37]- [38] with efficient self-driving algorithms; such as Robust Cruise Control [39]- [40].…”

Automated Driving

“…With the LiDAR technology, obstacles that are above the ground level could be easily recognized; however, in these off-road conditions it cannot be assumed that the condition of the terrain is always in good condition and the identification of negative obstacles is of great importance. That is why research projects are being developed especially dedicated to the identification of such obstacles, such as the case of Shang et al (2015), where a different set up for the LiDAR sensors is presented in order to identify the negative obstacles in nonurbanized environments. They were the winners of the "Overcome Danger 2014," a ground vehicle challenge supported by the Chinese army, similar to the DARPA Grand Challenge of the USA.…”