Three-dimensional Mapping with Augmented Navigation Cost through Deep Learning
Resumo
This work addresses the problem of mapping terrain features based on inertial and LiDAR measurements to estimate the navigation cost for an autonomous ground robot. Unlike most indoor applications, where surfaces are usually human-made, flat, and structured, external environments may be unpredictable regarding the types and conditions of the travel surfaces, such as traction characteristics and inclination. Attaining full autonomy in outdoor environments requires a mobile ground robot to perform the fundamental localization and mapping tasks in unfamiliar environments, but with the added challenge of unknown terrain conditions. A fuller representation of the environment is undamental to increase confidence and to reduce navigation costs. To this end, we propose a methodology composed of five main steps: i) speed-invariant inertial transformation; ii) roughness level classification; iii) navigation cost estimation; iv) sensor fusion through Deep Learning; and v) estimation of navigation costs for untraveled regions. To validate the methodology, we carried out experiments using ground robots in different outdoor environments with different terrain characteristics. Results show that the terrain maps thus obtained are a faithful representation of outdoor environments allowing for accurate and reliable path planning.
Referências
DuPont, E.M., Moore, C.A., Collins, E.G., Coyle, E.: Frequency response method for terrain classification in autonomous ground vehicles. Autonomous Robots 24(4), 337–347 (May 2008).
Dutta, A., Dasgupta, P.: Ensemble learning with weak classifiers for fast and reliable unknown terrain classification using mobile robots. IEEE Transactions on Systems, Man, and Cybernetics: Systems 47(11), 2933–2944 (2017).
Genesio, N., Abuhashim, T., Solari, F., Chessa, M., Natale, L.: Mobility map computations for autonomous navigation using an RGBD sensor. CoRR (2016).
Guerrero, J.A., Jaud, M., Lenain, R., Rouveure, R., Faure, P.: Towards lidar-radar based terrain mapping. In: IEEE Int. Workshop on Advanced Robotics and its Social Impacts (ARSO). pp. 1–6 (June 2015).
Nardi, L., Stachniss, C.: Actively Improving Robot Navigation On Different Terrains Using Gaussian Process Mixture Models. In: IEEE ICRA (03 2019).
Oliveira, F.G., Alves Neto, A., Borges, P., Campos, M.F.M., Macharet, D.G.: Augmented Vector Field Navigation Cost Mapping using Inertial Sensors. In: 19th Int. Conf. on Advanced Robotics (ICAR). pp. 388–393 (Dec 2019).
Oliveira, F.G., Santos, E.R.S., Alves Neto, A., Campos, M.F.M., Macharet, D.G.: Speed-invariant terrain roughness classification and control based on inertial sensors. In: 2017 Latin American Robotics Symposium (LARS) and 2017 Brazilian Symposium on Robotics (SBR). pp. 1–6 (Nov 2017).
Ono, M., Fuchs, T.J., Steffy, A., Maimone, M., Yen, J.: Risk-aware planetary rover operation: Autonomous terrain classification and path planning. In: IEEE Aerospace Conf. pp. 1–10 (March 2015).
Otte, S., Laible, S., Hanten, R., Zell, A.: Robust visual terrain classification with recurrent neural networks. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (01 2015).
Pfrunder, A., Borges, P.V.K., Romero, A.R., Catt, G., Elfes, A.: Real-time autonomous ground vehicle navigation in heterogeneous environments using a 3d lidar. In: IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS) (2017).
Rao, K.R., Kim, D.N., Hwang, J.J.: Fast Fourier Transform Algorithms and Applications. Springer Publishing Company, Incorporated, 1st edn. (2010).
Sebastian, B., Ren, H., Ben-Tzvi, P.: Neural network based heterogeneous sensor fusion for robot motion planning. In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE (Nov 2019).
