In this study, we address generalized autonomous mobile robot exploration of unknown environments where a robotic agent learns a traversability model and builds a spatial model of the environment. The agent can benefit from the model learned online in distinguishing what terrains are easy to traverse and which should be avoided. The proposed solution enables the learning of multiple traversability models, each associated with a particular locomotion gait, a walking pattern of a multi-legged walking robot. We propose to address the simultaneous learning of the environment and traversability models by a decoupled approach. Thus, navigation waypoints are generated using the current spatial and traversability models to gain the information necessary to improve the particular model during the robot's motion in the environment. From the set of possible waypoints, the decision on where to navigate next is made based on the solution of the generalized traveling salesman problem that allows taking into account a planning horizon longer than a single myopic decision. The proposed approach has been verified in simulated scenarios and experimental deployments with a real hexapod walking robot with two locomotion gaits, suitable for different terrains. Based on the achieved results, the proposed method exploits the online learned traversability models and further supports the selection of the most appropriate locomotion gait for the particular terrain types.

Computational Robotics Laboratory Faculty of Electrical Engineering Czech Technical University Prague Prague Czechia

Zobrazit více v PubMed

Azpúrna H., Campos M. F. M., Macharet D. G. (2021). Three-dimensional terrain aware autonomous exploration for subterranean and confined spaces. IEEE Int. Conf. Robotics Automation (ICRA), 2443. –2449. 10.1109/ICRA48506.2021.9561099 DOI

Baleia J., Santana P., Barata J. (2015). On exploiting haptic cues for self-supervised learning of depth-based robot navigation affordances. J. Intell. Robot. Syst. 80, 455–474. 10.1007/s10846-015-0184-4 DOI

Bayer J., Faigl J. (2021). “Decentralized topological mapping for multi-robot autonomous exploration under low-bandwidth communication,” in European Conference on Mobile Robots (Bonn, Germany: ECMR; ), 1–7. 10.1109/ECMR50962.2021.9568824 DOI

Bayer J., Faigl J. (2019). “Speeded up elevation map for exploration of large-scale subterranean environments,” In 2019 Modelling and Simulation for Autonomous Systems (Palermo, Italy: MESAS; ), 192–202. 10.1007/978-3-030-43890-615 DOI

Bayer J., Faigl J. (2020). “Speeded up elevation map for exploration of large-scale subterranean environments,” in 2020 Modelling and Simulation for autonomous systems (MESAS). 190–202.

Bekhti M. A., Kobayashi Y. (2016). “Prediction of vibrations as a measure of terrain traversability in outdoor structured and natural environments,” in Image and video technology, 282–294. 10.1007/978-3-319-29451-3_23 DOI

Belter D., Wietrzykowski J., Skrzypczyński P. (2019). Employing natural terrain semantics in motion planning for a multi-legged robot. J. Intell. Robot. Syst. 93, 723–743. 10.1007/s10846-018-0865-x DOI

Binney J., Sukhatme G. S. (2012). Branch and bound for informative path planning. IEEE Int. Conf. Robotics Automation (ICRA), 2147. –2154. 10.1109/ICRA.2012.6224902 DOI

Bourgault F., Makarenko A. A., Williams S. B., Grocholsky B., Durrant-Whyte H. F. (2002). “Information based adaptive robotic exploration,” in IEEE/RSJ international conference on intelligent robots and systems (Lausanne, Switzerland: IROS; ), 540–545. 10.1109/IRDS.2002.1041446 DOI

Bradley D. M., Chang J. K., Silver D., Powers M., Herman H., Rander P., et al. (2015). “Scene understanding for a high-mobility walking robot,” in IEEE/RSJ international conference on intelligent robots and systems (Hamburg, Germany: IROS; ), 1144–1151. 10.1109/IROS.2015.7353514 DOI

Brown D., Webster G. (2010). Now a stationary research platform, NASA’s Mars rover Spirit starts a new chapter in red planet scientific studies. Pasadena, CA: NASA Press Release.

Carrillo H., Dames P., Kumar V., Castellanos J. A. (2018). Autonomous robotic exploration using a utility function based on Rényi’s general theory of entropy. Auton. Robots 42, 235–256. 10.1007/s10514-017-9662-9 DOI

Charrow B., Liu S., Kumar V., Michael N. (2015). Information-theoretic mapping using cauchy-schwarz quadratic mutual information. IEEE Int. Conf. Robotics Automation (ICRA), 4791–4798. 10.1109/ICRA.2015.7139865 DOI

Dang T., Tranzatto M., Khattak S., Mascarich F., Alexis K., Hutter M. (2020). Graph-based subterranean exploration path planning using aerial and legged robots. J. Field Robot. 37, 1363–1388. 10.1002/rob.21993 DOI

Faigl J., Čížek P. (2019). Adaptive locomotion control of hexapod walking robot for traversing rough terrains with position feedback only. Robotics Aut. Syst. 116, 136–147. 10.1016/j.robot.2019.03.008 DOI

Faigl J., Kulich M. (2013). “On determination of goal candidates in frontier-based multi-robot exploration,” in European conference on mobile robots (Barcelona, Spain: ECMR; ), 210–215. 10.1109/ECMR.2013.6698844 DOI

Faigl J., Kulich M., Přeučil L. (2012). “Goal assignment using distance cost in multi-robot exploration,” in IEEE/RSJ international conference on intelligent robots and systems (Vilamoura-Algarve, Portugal: IROS; ), 3741–3746. 10.1109/IROS.2012.6385660 DOI

Fankhauser P., Bloesch M., Gehring C., Hutter M., Siegwart R. (2014). World Scientific, 433–440.Robot-centric elevation mapping with uncertainty estimates Mob. Serv. Robot.

Forouhar M., Čížek P., Faigl J. (2021). “Scarab II: A small versatile six-legged walking robot,” in 5th full-day workshop on legged robots at IEEE international conference on robotics and automation (Xi’an, China: ICRA; ), 1–2.

Fritzke B. (1994). “A growing neural gas network learns topologies,” in Conference on neural information processing systems (Denver, CO: NIPS; ), 625–632.

Gonzalez R., Iagnemma K. (2018). Slippage estimation and compensation for planetary exploration rovers. State of the art and future challenges. J. Field Robotics 35, 564–577. 10.1002/rob.21761 DOI

Guastella D. C., Muscato G. (2021). Learning-based methods of perception and navigation for ground vehicles in unstructured environments: A review. Sensors 21, 73. 10.3390/s21010073 PubMed DOI PMC

Guerrero E., Bonin-Font F., Oliver G. (2021). Adaptive visual information gathering for autonomous exploration of underwater environments. IEEE Access 9, 136487–136506. 10.1109/ACCESS.2021.3117343 DOI

Haddeler G., Chan J., You Y., Verma S., Adiwahono A. H., Meng Chew C. (2020). “Explore bravely: Wheeled-legged robots traverse in unknown rough environment,” in IEEE/RSJ international conference on intelligent robots and systems (Las Vegas, NV: IROS; ), 7521–7526. 10.1109/IROS45743.2020.9341610 DOI

Helsgaun K. (2000). An effective implementation of the lin-kernighan traveling salesman heuristic. Eur. J. Operational Res. 126, 106–130. 10.1016/s0377-2217(99)00284-2 DOI

Hollinger G. A., Sukhatme G. S. (2014). Sampling-based robotic information gathering algorithms. Int. J. Rob. Res. 33, 1271–1287. 10.1177/0278364914533443 DOI

Homberger T., Bjelonic M., Kottege N., Borges P. V. K. (2016). “Terrain-dependant control of hexapod robots using vision,” in International symposium on experimental robotics (Nagasaki, Japan: ISER; ), 92–102. 10.1007/978-3-319-50115-4_9 DOI

Karolj V., Viseras A., Merino L., Shutin D. (2020). An integrated strategy for autonomous exploration of spatial processes in unknown environments. Sensors 20, 3663. 10.3390/s20133663 PubMed DOI PMC

Kottege N., Parkinson C., Moghadam P., Elfes A., Singh S. P. N. (2015). Energetics-informed hexapod gait transitions across terrains. IEEE Int. Conf. Robotics Automation (ICRA), 5140–5147. 10.1109/ICRA.2015.7139915 DOI

Krajník T., Fentanes J. P., Santos J. M., Duckett T. (2017). Fremen: Frequency map enhancement for long-term mobile robot autonomy in changing environments. IEEE Trans. Robot. 33, 964–977. 10.1109/TRO.2017.2665664 DOI

Krüsi P., Bosse M., Siegwart R. (2016). Driving on point clouds: Motion planning, trajectory optimization, and terrain assessment in generic nonplanar environments. J. Field Robot. 34, 940–984. 10.1002/rob.21700 DOI

Lin B., Song S. (1993). Dynamic modeling, stability and energy efficiency of a quadrupedal walking machine. J. Robot. Syst. 18, 657–670. 10.1002/rob.8104 DOI

Luo W., Sycara K. (2018). Adaptive sampling and online learning in multi-robot sensor coverage with mixture of Gaussian processes. IEEE Int. Conf. Robotics Automation (ICRA), 6359–6364. 10.1109/ICRA.2018.8460473 DOI

Ma K.-C., Liu L., Heidarsson H. K., Sukhatme G. S. (2018). Data-driven learning and planning for environmental sampling. J. Field Robot. 35, 643–661. 10.1002/rob.21767 DOI

Makarenko A. A., Williams S. B., Bourgault F., Durrant-Whyte H. F. (2002). in IEEE/RSJ international conference on intelligent robots and systems, 1, An experiment in integrated exploration534–539. 10.1109/IRDS.2002.1041445 (IROS) DOI

Mann H. B., Whitney D. R. (1947). On a test of whether one of two random variables is stochastically larger than the other. Ann. Math. Stat. 18, 50–60. 10.1214/aoms/1177730491 DOI

Martin S., Corke P. (2014). Long-term exploration & tours for energy constrained robots with online proprioceptive traversability estimation. IEEE Int. Conf. Robotics Automation (ICRA), 5778–5785. 10.1109/ICRA.2014.6907708 DOI

Mayuku O., Surgenor B. W., Marshall J. A. (2021). “A self-supervised near-to-far approach for terrain-adaptive off-road autonomous driving,” in IEEE international conference on robotics and automation (Xi’an, China: ICRA; ), 14054–14060. 10.1109/ICRA48506.2021.9562029 DOI

McGhee R. B., Frank A. A. (1968). On the stability properties of quadruped creeping gaits. Math. Biosci. 3, 331–351. 10.1016/0025-5564(68)90090-4 DOI

Moravec H., Elfes A. (1985). “High resolution maps from wide angle sonar,” in 1985 IEEE international conference on robotics and automation proceedings, 116–121. 10.1109/ROBOT.1985.1087316 DOI

Noon C. E., Bean J. C. (1993). An efficient transformation of the generalized traveling salesman problem. INFOR Inf. Syst. Operational Res. 31, 39–44. 10.1080/03155986.1993.11732212 DOI

Noon C. E. (1988). The generalized traveling salesman problem. Ann Arbor, MI: Ph.D. thesis, University of Michigan.

O’Callaghan S., Ramos F. T., Durrant-Whyte H. (2009). Contextual occupancy maps using Gaussian processes. IEEE Int. Conf. Robotics Automation (ICRA), 1054–1060. 10.1109/ROBOT.2009.5152754 DOI

O’Meadhra C., Tabib W., Michael N. (2019). Variable resolution occupancy mapping using Gaussian mixture models. IEEE Robot. Autom. Lett. 4, 2015–2022. 10.1109/LRA.2018.2889348 DOI

Ossenkopf M., Castro G., Pessacg F., Geihs K., De Cristóforis P. (2019). “Long-Horizon Active SLAM system for multi-agent coordinated exploration,” in European conference on mobile robots (Prague, Czech Republic: ECMR; ), 1–6. 10.1109/ECMR.2019.8870952 DOI

Papadakis P. (2013). Terrain traversability analysis methods for unmanned ground vehicles: A survey. Eng. Appl. Artif. Intell. 26, 1373–1385. 10.1016/j.engappai.2013.01.006 DOI

Pasolli E., Melgani F. (2011). Gaussian process regression within an active learning scheme. IEEE Int. Geoscience Remote Sens. Symposium, 3574–3577. 10.1109/IGARSS.2011.6049994 DOI

Prágr M., Čížek P., Bayer J., Faigl J. (2019a). “Online incremental learning of the terrain traversal cost in autonomous exploration,” in Robotics: Science and systems, (RSS) (Freiburg im Breisgau, Germany). 1–10. 10.15607/RSS.2019.XV.040 DOI

Prágr M., Čížek P., Faigl J. (2018). “Cost of transport estimation for legged robot based on terrain features inference from aerial scan,” in IEEE/RSJ international conference on intelligent robots and systems (IROS) (Prague, Czech Republic: IEEE; ), 1745–1750. 10.1109/IROS.2018.8593374 DOI

Prágr M., Čížek P., Faigl J. (2019b). “Incremental learning of traversability cost for aerial reconnaissance support to ground units,” in 2018 modelling and simulation for autonomous systems (Prague, Czech Republic: MESAS; ), 412–421. 10.1007/978-3-030-14984-0_30 DOI

Prudent Y., Ennaji A. (2005). An incremental growing neural gas learns topologies. Int. Jt. Conf. Neural Netw. (IJCNN) 2, 1211–1216. 10.1109/IJCNN.2005.1556026 DOI

Quann M., Ojeda L., Smith W., Rizzo D., Castanier M., Barton K. (2020). Off-road ground robot path energy cost prediction through probabilistic spatial mapping. J. Field Robot. 37, 421–439. 10.1002/rob.21927 DOI

Quigley M., Conley K., Gerkey B. P., Faust J., Foote T., Leibs J., et al. (2009). ICRA Workshop on Open Source Software, 1–6.Ros: An open-source robot operating system.

Ramos F., Ott L. (2016). Hilbert maps: Scalable continuous occupancy mapping with stochastic gradient descent. Int. J. Rob. Res. 35, 1717–1730. 10.1177/0278364916684382 DOI

Rasmussen C. E., Williams C. K. I. (2006). Gaussian processes for machine learning. Adaptive computation and machine learning. Cambridge, Mass: MIT Press.

Rényi A. (1961). On measures of entropy and information. Berkeley Symposium Math. Statistics Probab., 547–561.

Rhodes C., Liu C., Chen W.-H. (2020). “Informative path planning for gas distribution mapping in cluttered environments,” in IEEE/RSJ international conference on intelligent robots and systems (Las Vegas, NV: IROS; ), 6726–6732. 10.1109/IROS45743.2020.9341781 DOI

Schultz A. C., Adams W., Yamauchi B. (1999). Integrating exploration, localization, navigation and planning with a common representation. Auton. Robots 6, 293–308. 10.1023/A:1008936413435 DOI

Shi Y., Wang N., Zheng J., Zhang Y., Yi S., Luo W., et al. (2020). “Adaptive informative sampling with environment partitioning for heterogeneous multi-robot systems,” in IEEE/RSJ international conference on intelligent robots and systems (Las Vegas, NV: IROS; ), 11718–11723. 10.1109/IROS45743.2020.9341711 DOI

Singh A., Krause A., Guestrin C., Kaiser W., Batalin M. (2007). “Efficient planning of informative paths for multiple robots,” in International joint conference on artifical intelligence, 2204–2211.

Sofman B., Lin E., Bagnell J. A., Cole J., Vandapel N., Stentz A. (2006). Improving robot navigation through self-supervised online learning. J. Field Robot. 23, 1059–1075. 10.1002/rob.20169 DOI

Srinivas N., Krause A., Kakade S., Seeger M. (2010). “Gaussian process optimization in the bandit setting: No regret and experimental design,” in Intl. Conf. International conference on machine learning (ICML) (Haifa, Israel, 1015–1022.

Stachniss C., Grisetti G., Burgard W. (2005). “Information gain-based exploration using rao-blackwellized particle filters,” in Robotics: Science and systems, 1–8. 10.15607/RSS.2005.I.009 DOI

Stelzer A., Hirschmüller H., Görner M. (2012). Stereo-vision-based navigation of a six-legged walking robot in unknown rough terrain. Int. J. Rob. Res. 31, 381–402. 10.1177/0278364911435161 DOI

Vallvé J., Andrade-Cetto J. (2015). Potential information fields for mobile robot exploration. Robotics Aut. Syst. 69, 68–79. 10.1016/j.robot.2014.08.009 DOI

Viseras A., Shutin D., Merino L. (2019). Robotic active information gathering for spatial field reconstruction with rapidly-exploring random trees and online learning of Gaussian processes. Sensors 19, 1016. 10.3390/s19051016 PubMed DOI PMC

Wang J., Englot B. (2016). Fast, accurate Gaussian process occupancy maps via test-data octrees and nested Bayesian fusion. IEEE Int. Conf. Robotics Automation (ICRA), 1003–1010. 10.1109/ICRA.2016.7487232 DOI

Wermelinger M., Fankhauser P., Diethelm R., Krüsi P., Siegwart R., Hutter M. (2016). “Navigation planning for legged robots in challenging terrain,” in IEEE/RSJ international conference on intelligent robots and systems, 1184–1189. 10.1109/IROS.2016.7759199 DOI

Yamauchi B. (1997). A frontier-based approach for autonomous exploration. CIRA (IEEE), 146–151. 10.1109/CIRA.1997.613851 DOI

Zlot R., Stentz A. (2006). Market-based multirobot coordination for complex tasks. Int. J. Rob. Res. 25, 73–101. 10.1177/0278364906061160 DOI