LIDAR and stereo combination for traversability assessment of off-road robotic vehicles
| Autor: | Rainer Worst, Annalisa Milella, Giulio Reina |
|---|---|
| Přispěvatelé: | Reina, Giulio, Milella, Annalisa, Worst, Rainer, Publica |
| Jazyk: | angličtina |
| Rok vydání: | 2016 |
| Předmět: |
Sensor combination
0209 industrial biotechnology Exploit Computer science General Mathematics Terrain 02 engineering and technology Navigation systems 01 natural sciences 020901 industrial engineering & automation Ground detection Sensor integration Self-learning classification Lidar data Computer vision Navigation system Intelliegent vehicle business.industry 010401 analytical chemistry Robotics Unmanned ground vehicles Driving automation 0104 chemical sciences Computer Science Applications Robotic Lidar Control and Systems Engineering Robotic vehicles Artificial intelligence Online learning strategy business Classifier (UML) Software |
| Zdroj: | Robotica (Camb., Print) 34 (2016): 2823–2841. doi:10.1017/S0263574715000442 info:cnr-pdr/source/autori:Giulio Reina; Annalisa Milella; Rainer Worst/titolo:LIDAR and stereo combination for traversability assessment of Off-Road Robotic Vehicles/doi:10.1017%2FS0263574715000442/rivista:Robotica (Camb., Print)/anno:2016/pagina_da:2823/pagina_a:2841/intervallo_pagine:2823–2841/volume:34 |
| DOI: | 10.1017/S0263574715000442 |
| Popis: | SUMMARYReliable assessment of terrain traversability using multi-sensory input is a key issue for driving automation, particularly when the domain is unstructured or semi-structured, as in natural environments. In this paper, LIDAR-stereo combination is proposed to detect traversable ground in outdoor applications. The system integrates two self-learning classifiers, one based on LIDAR data and one based on stereo data, to detect the broad class of drivable ground. Each single-sensor classifier features two main stages: an adaptive training stage and a classification stage. During the training stage, the classifier automatically learns to associate geometric appearance of 3D data with class labels. Then, it makes predictions based on past observations. The output obtained from the single-sensor classifiers are statistically combined in order to exploit their individual strengths and reach an overall better performance than could be achieved by using each of them separately. Experimental results, obtained with a test bed platform operating in rural environments, are presented to validate and assess the performance of this approach, showing its effectiveness and potential applicability to autonomous navigation in outdoor contexts. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|