Learning agile and dynamic motor skills for legged robots
Legged robots pose one of the greatest challenges in robotics. Dynamic and agile maneuvers of animals cannot be imitated by existing methods that are crafted by humans. A compelling alternative is reinforcement learning, which requires minimal craftsmanship and promotes the natural evolution of a co...
Uloženo v:
| Vydáno v: | Science robotics Ročník 4; číslo 26 |
|---|---|
| Hlavní autoři: | , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
United States
16.01.2019
|
| ISSN: | 2470-9476, 2470-9476 |
| On-line přístup: | Zjistit podrobnosti o přístupu |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Legged robots pose one of the greatest challenges in robotics. Dynamic and agile maneuvers of animals cannot be imitated by existing methods that are crafted by humans. A compelling alternative is reinforcement learning, which requires minimal craftsmanship and promotes the natural evolution of a control policy. However, so far, reinforcement learning research for legged robots is mainly limited to simulation, and only few and comparably simple examples have been deployed on real systems. The primary reason is that training with real robots, particularly with dynamically balancing systems, is complicated and expensive. In the present work, we introduce a method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby leveraging fast, automated, and cost-effective data generation schemes. The approach is applied to the ANYmal robot, a sophisticated medium-dog-sized quadrupedal system. Using policies trained in simulation, the quadrupedal machine achieves locomotion skills that go beyond what had been achieved with prior methods: ANYmal is capable of precisely and energy-efficiently following high-level body velocity commands, running faster than before, and recovering from falling even in complex configurations. |
|---|---|
| AbstractList | Legged robots pose one of the greatest challenges in robotics. Dynamic and agile maneuvers of animals cannot be imitated by existing methods that are crafted by humans. A compelling alternative is reinforcement learning, which requires minimal craftsmanship and promotes the natural evolution of a control policy. However, so far, reinforcement learning research for legged robots is mainly limited to simulation, and only few and comparably simple examples have been deployed on real systems. The primary reason is that training with real robots, particularly with dynamically balancing systems, is complicated and expensive. In the present work, we introduce a method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby leveraging fast, automated, and cost-effective data generation schemes. The approach is applied to the ANYmal robot, a sophisticated medium-dog-sized quadrupedal system. Using policies trained in simulation, the quadrupedal machine achieves locomotion skills that go beyond what had been achieved with prior methods: ANYmal is capable of precisely and energy-efficiently following high-level body velocity commands, running faster than before, and recovering from falling even in complex configurations. Legged robots pose one of the greatest challenges in robotics. Dynamic and agile maneuvers of animals cannot be imitated by existing methods that are crafted by humans. A compelling alternative is reinforcement learning, which requires minimal craftsmanship and promotes the natural evolution of a control policy. However, so far, reinforcement learning research for legged robots is mainly limited to simulation, and only few and comparably simple examples have been deployed on real systems. The primary reason is that training with real robots, particularly with dynamically balancing systems, is complicated and expensive. In the present work, we introduce a method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby leveraging fast, automated, and cost-effective data generation schemes. The approach is applied to the ANYmal robot, a sophisticated medium-dog-sized quadrupedal system. Using policies trained in simulation, the quadrupedal machine achieves locomotion skills that go beyond what had been achieved with prior methods: ANYmal is capable of precisely and energy-efficiently following high-level body velocity commands, running faster than before, and recovering from falling even in complex configurations.Legged robots pose one of the greatest challenges in robotics. Dynamic and agile maneuvers of animals cannot be imitated by existing methods that are crafted by humans. A compelling alternative is reinforcement learning, which requires minimal craftsmanship and promotes the natural evolution of a control policy. However, so far, reinforcement learning research for legged robots is mainly limited to simulation, and only few and comparably simple examples have been deployed on real systems. The primary reason is that training with real robots, particularly with dynamically balancing systems, is complicated and expensive. In the present work, we introduce a method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby leveraging fast, automated, and cost-effective data generation schemes. The approach is applied to the ANYmal robot, a sophisticated medium-dog-sized quadrupedal system. Using policies trained in simulation, the quadrupedal machine achieves locomotion skills that go beyond what had been achieved with prior methods: ANYmal is capable of precisely and energy-efficiently following high-level body velocity commands, running faster than before, and recovering from falling even in complex configurations. |
| Author | Tsounis, Vassilios Hwangbo, Jemin Dosovitskiy, Alexey Bellicoso, Dario Lee, Joonho Hutter, Marco Koltun, Vladlen |
| Author_xml | – sequence: 1 givenname: Jemin orcidid: 0000-0002-3444-8079 surname: Hwangbo fullname: Hwangbo, Jemin email: jhwangbo@ethz.ch organization: Robotic Systems Lab, ETH Zurich, Zurich, Switzerland. jhwangbo@ethz.ch – sequence: 2 givenname: Joonho orcidid: 0000-0002-5072-7385 surname: Lee fullname: Lee, Joonho organization: Robotic Systems Lab, ETH Zurich, Zurich, Switzerland – sequence: 3 givenname: Alexey orcidid: 0000-0003-1851-0976 surname: Dosovitskiy fullname: Dosovitskiy, Alexey organization: Intelligent Systems Lab, Intel, Munich, Germany – sequence: 4 givenname: Dario orcidid: 0000-0003-3856-0735 surname: Bellicoso fullname: Bellicoso, Dario organization: Robotic Systems Lab, ETH Zurich, Zurich, Switzerland – sequence: 5 givenname: Vassilios orcidid: 0000-0003-3428-8455 surname: Tsounis fullname: Tsounis, Vassilios organization: Robotic Systems Lab, ETH Zurich, Zurich, Switzerland – sequence: 6 givenname: Vladlen orcidid: 0000-0003-0858-0970 surname: Koltun fullname: Koltun, Vladlen organization: Intelligent Systems Lab, Intel, Santa Clara, CA, USA – sequence: 7 givenname: Marco orcidid: 0000-0002-4285-4990 surname: Hutter fullname: Hutter, Marco organization: Robotic Systems Lab, ETH Zurich, Zurich, Switzerland |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/33137755$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNjztPwzAYRS1UREvpL0BCHllS_LYzooqXFIkF5uiL40QGxy5xMvTfU0GRmO4Zju7VvUSLmKJD6JqSLaVM3WXrx9Skydu8BZil0ewMrZjQpCiFVot_vESbnD8IIVQrrgS7QEvOKddayhUqKwdj9LHH0PvgMMQWt4cIg7d4SFMacf70IWTcHTG4vnct_hnOV-i8g5Dd5pRr9P748LZ7LqrXp5fdfVVYQdVUMN1RqUA75YC0EgzpSKdMR60zsrGqZNoKZjRwrqltbckFaNNIzShYqx1bo9vf3v2YvmaXp3rw2boQILo055qJo2uYIuqo3pzUuRlcW-9HP8B4qP_usm-Sx1wg |
| CitedBy_id | crossref_primary_10_1109_LRA_2020_3007451 crossref_primary_10_1109_LRA_2022_3218167 crossref_primary_10_3389_fncir_2021_743888 crossref_primary_10_3389_frobt_2022_854212 crossref_primary_10_1007_s42235_023_00452_9 crossref_primary_10_1155_2020_8854411 crossref_primary_10_1007_s43154_022_00082_9 crossref_primary_10_1109_TNNLS_2021_3117878 crossref_primary_10_1371_journal_pone_0246102 crossref_primary_10_1109_TMECH_2023_3241302 crossref_primary_10_1109_ACCESS_2021_3068769 crossref_primary_10_1109_ACCESS_2020_3042874 crossref_primary_10_3389_fnbot_2021_655330 crossref_primary_10_1109_TRO_2023_3262108 crossref_primary_10_3389_frobt_2022_852270 crossref_primary_10_1016_j_aei_2022_101661 crossref_primary_10_1109_LRA_2024_3374190 crossref_primary_10_1126_scirobotics_abg5561 crossref_primary_10_1109_LRA_2023_3320827 crossref_primary_10_1109_TRO_2020_3046415 crossref_primary_10_1126_scirobotics_ads5033 crossref_primary_10_3390_mi13101688 crossref_primary_10_3390_s23073762 crossref_primary_10_1038_s41598_023_48338_4 crossref_primary_10_3390_biomimetics9110691 crossref_primary_10_1007_s10489_019_01510_8 crossref_primary_10_1007_s42235_023_00442_x crossref_primary_10_1002_admt_202400992 crossref_primary_10_3390_molecules28052232 crossref_primary_10_1017_S0140525X22000814 crossref_primary_10_1038_s41467_022_34324_3 crossref_primary_10_1109_ACCESS_2023_3304992 crossref_primary_10_1109_TNNLS_2024_3446371 crossref_primary_10_3389_fnbot_2025_1649870 crossref_primary_10_7746_jkros_2025_20_3_495 crossref_primary_10_1109_TRO_2024_3504132 crossref_primary_10_1109_ACCESS_2022_3172492 crossref_primary_10_3389_frobt_2021_629523 crossref_primary_10_1016_j_mser_2025_101054 crossref_primary_10_1109_TRO_2020_3047515 crossref_primary_10_3389_frobt_2023_1282299 crossref_primary_10_1093_nsr_nwac214 crossref_primary_10_3390_app11041587 crossref_primary_10_1186_s10033_020_00493_9 crossref_primary_10_1126_scirobotics_adv3604 crossref_primary_10_1126_scirobotics_abb9764 crossref_primary_10_1038_s44182_023_00006_5 crossref_primary_10_1016_j_neunet_2022_10_016 crossref_primary_10_3389_frobt_2024_1337722 crossref_primary_10_3390_act14040199 crossref_primary_10_1109_LRA_2023_3304561 crossref_primary_10_1126_scirobotics_adu3922 crossref_primary_10_1109_JAS_2025_125552 crossref_primary_10_1177_02783649231224053 crossref_primary_10_1109_TNNLS_2019_2955699 crossref_primary_10_1049_ccs2_12002 crossref_primary_10_1109_LRA_2023_3270034 crossref_primary_10_1109_TRO_2023_3284362 crossref_primary_10_1109_LRA_2023_3281290 crossref_primary_10_1109_TIE_2024_3429576 crossref_primary_10_1109_TITS_2020_3023788 crossref_primary_10_1016_j_arcontrol_2024_100948 crossref_primary_10_1007_s11432_022_3696_5 crossref_primary_10_1109_LRA_2024_3459797 crossref_primary_10_1109_LRA_2024_3457379 crossref_primary_10_1109_TRO_2024_3430711 crossref_primary_10_3390_app14125213 crossref_primary_10_1007_s40430_025_05389_0 crossref_primary_10_1109_ACCESS_2023_3311141 crossref_primary_10_1016_j_ymssp_2021_108284 crossref_primary_10_3390_drones8100554 crossref_primary_10_1108_IR_01_2025_0015 crossref_primary_10_1109_LRA_2021_3100269 crossref_primary_10_1038_s41467_020_19424_2 crossref_primary_10_3389_fnbot_2023_1089270 crossref_primary_10_1109_ACCESS_2023_3301175 crossref_primary_10_1155_2022_3551508 crossref_primary_10_1016_j_mechmachtheory_2021_104358 crossref_primary_10_1109_LRA_2022_3188108 crossref_primary_10_1007_s42235_023_00432_z crossref_primary_10_1016_j_procs_2024_11_001 crossref_primary_10_1109_TNNLS_2021_3124366 crossref_primary_10_3390_machines12120902 crossref_primary_10_1109_LRA_2025_3541432 crossref_primary_10_1007_s42235_024_00517_3 crossref_primary_10_1109_TMECH_2024_3353915 crossref_primary_10_3390_s24186070 crossref_primary_10_1186_s10033_020_00485_9 crossref_primary_10_1038_s41598_019_51308_4 crossref_primary_10_1038_s42256_021_00320_3 crossref_primary_10_1007_s10489_024_05782_7 crossref_primary_10_1007_s10514_021_09974_9 crossref_primary_10_1088_1748_3190_ac92b3 crossref_primary_10_1088_1361_665X_adf37f crossref_primary_10_3390_buildings12112027 crossref_primary_10_1177_02783649241273645 crossref_primary_10_1016_j_birob_2023_100091 crossref_primary_10_1016_j_jestch_2024_101783 crossref_primary_10_1109_ACCESS_2020_3016312 crossref_primary_10_1126_scirobotics_abk2822 crossref_primary_10_1088_2634_4386_ac1b76 crossref_primary_10_1038_s41598_024_83749_x crossref_primary_10_1088_1748_3190_ac9ef5 crossref_primary_10_1126_scirobotics_adh5401 crossref_primary_10_1016_j_oceaneng_2023_113620 crossref_primary_10_1177_02783649241260428 crossref_primary_10_1016_j_ast_2023_108689 crossref_primary_10_1017_S0263574721001600 crossref_primary_10_1109_LRA_2020_2979656 crossref_primary_10_3389_frobt_2022_969380 crossref_primary_10_1177_1464419320933382 crossref_primary_10_1038_s41598_024_58380_5 crossref_primary_10_1109_LRA_2025_3577526 crossref_primary_10_1109_LRA_2025_3595037 crossref_primary_10_1007_s12559_022_10080_w crossref_primary_10_1016_j_neucom_2023_126986 crossref_primary_10_1007_s11012_022_01475_y crossref_primary_10_1016_j_robot_2020_103703 crossref_primary_10_1109_LRA_2025_3573169 crossref_primary_10_3390_biomimetics8020168 crossref_primary_10_1007_s41315_019_00101_7 crossref_primary_10_1109_LRA_2022_3142730 crossref_primary_10_1088_1748_3190_ac6847 crossref_primary_10_1109_MRA_2022_3207664 crossref_primary_10_1007_s13042_022_01639_y crossref_primary_10_1155_2020_3507679 crossref_primary_10_1109_TASE_2023_3310945 crossref_primary_10_3390_electronics12071564 crossref_primary_10_1109_LRA_2021_3061308 crossref_primary_10_1126_scirobotics_ads6790 crossref_primary_10_3390_biomimetics8010112 crossref_primary_10_3390_s24227306 crossref_primary_10_1109_TIE_2020_2973893 crossref_primary_10_3389_fnbot_2020_00014 crossref_primary_10_1109_LRA_2019_2925731 crossref_primary_10_1093_icb_icae121 crossref_primary_10_1109_OJIES_2025_3567112 crossref_primary_10_1126_scirobotics_adg0279 crossref_primary_10_1109_LRA_2025_3577876 crossref_primary_10_7717_peerj_cs_1720 crossref_primary_10_1049_cit2_12304 crossref_primary_10_1109_LRA_2022_3211785 crossref_primary_10_1016_j_ifacol_2020_12_1205 crossref_primary_10_1088_1748_3190_ab782a crossref_primary_10_1109_LRA_2021_3136645 crossref_primary_10_7736_JKSPE_024_037 crossref_primary_10_1038_s41598_022_08755_3 crossref_primary_10_1016_j_oceaneng_2024_120139 crossref_primary_10_1002_adma_202002800 crossref_primary_10_1016_j_rcim_2022_102360 crossref_primary_10_1109_LRA_2025_3575648 crossref_primary_10_1016_j_neucom_2023_126885 crossref_primary_10_1007_s12555_025_0127_1 crossref_primary_10_1177_02783649251349225 crossref_primary_10_1038_s41598_023_34007_z crossref_primary_10_1088_1748_3190_ac6e1b crossref_primary_10_1007_s42235_023_00347_9 crossref_primary_10_1109_TRO_2024_3352969 crossref_primary_10_1007_s12541_023_00885_6 crossref_primary_10_1016_j_eswa_2025_127651 crossref_primary_10_1080_01691864_2019_1679251 crossref_primary_10_1007_s42235_023_00468_1 crossref_primary_10_1109_TRO_2023_3286046 crossref_primary_10_3389_fbioe_2022_804826 crossref_primary_10_1109_TNNLS_2022_3207346 crossref_primary_10_1038_s41467_024_50131_4 crossref_primary_10_1016_j_oceaneng_2025_121978 crossref_primary_10_3390_electronics11132031 crossref_primary_10_1109_LCSYS_2019_2960442 crossref_primary_10_1177_02783649231188387 crossref_primary_10_3389_fnbot_2019_00059 crossref_primary_10_3390_biomimetics9040193 crossref_primary_10_3389_fnbot_2020_591128 crossref_primary_10_3389_fnbot_2022_1054239 crossref_primary_10_3390_drones7040225 crossref_primary_10_1109_ACCESS_2023_3278208 crossref_primary_10_1109_LRA_2021_3076955 crossref_primary_10_1126_scirobotics_abb2174 crossref_primary_10_3390_s23115194 crossref_primary_10_1109_LRA_2025_3592085 crossref_primary_10_1093_nsr_nwad298 crossref_primary_10_1109_TRO_2021_3084374 crossref_primary_10_1002_aisy_202100195 crossref_primary_10_1016_j_robot_2019_103362 crossref_primary_10_1038_d41586_019_00999_w crossref_primary_10_1109_TNNLS_2021_3099621 crossref_primary_10_1038_s42256_023_00743_0 crossref_primary_10_1109_ACCESS_2023_3321842 crossref_primary_10_3390_math13152466 crossref_primary_10_3390_robotics12040109 crossref_primary_10_1186_s10033_021_00578_z crossref_primary_10_1002_oca_3181 crossref_primary_10_1007_s40430_024_05028_0 crossref_primary_10_3389_fnbot_2021_627157 crossref_primary_10_3390_biomimetics9030132 crossref_primary_10_1016_j_nahs_2024_101468 crossref_primary_10_1186_s12984_023_01147_2 crossref_primary_10_3389_frobt_2022_1059026 crossref_primary_10_1016_j_neunet_2021_06_001 crossref_primary_10_1109_TSMC_2021_3096935 crossref_primary_10_1177_02783649211063225 crossref_primary_10_1016_j_neunet_2020_05_029 crossref_primary_10_1109_ACCESS_2020_3020590 crossref_primary_10_1109_TCDS_2023_3345539 crossref_primary_10_1007_s12555_023_0826_4 crossref_primary_10_1007_s42235_024_00509_3 crossref_primary_10_1109_LRA_2022_3177289 crossref_primary_10_1108_IR_02_2022_0046 crossref_primary_10_3390_s20030939 crossref_primary_10_1109_LRA_2022_3169309 crossref_primary_10_1126_scirobotics_adg7165 crossref_primary_10_1002_rnc_6825 crossref_primary_10_3390_act12030110 crossref_primary_10_1007_s42241_020_0028_y crossref_primary_10_1109_LRA_2023_3301274 crossref_primary_10_1016_j_birob_2025_100231 crossref_primary_10_1177_09544062241235079 crossref_primary_10_4018_JOEUC_369158 crossref_primary_10_1007_s10489_024_06115_4 crossref_primary_10_3390_s24154981 crossref_primary_10_1038_s42256_025_01065_z crossref_primary_10_3390_act12040157 crossref_primary_10_1109_LRA_2020_2974707 crossref_primary_10_1126_scirobotics_abm6010 crossref_primary_10_1038_s41586_023_06419_4 crossref_primary_10_1016_j_asr_2024_06_064 crossref_primary_10_1109_LRA_2025_3551637 crossref_primary_10_1109_TRO_2022_3226149 crossref_primary_10_1016_j_robot_2020_103515 crossref_primary_10_1109_ACCESS_2022_3151771 crossref_primary_10_1109_TRO_2023_3297015 crossref_primary_10_1109_TCYB_2021_3049555 crossref_primary_10_7717_peerj_cs_718 crossref_primary_10_1016_j_oceaneng_2021_108862 crossref_primary_10_1109_TIE_2025_3558030 crossref_primary_10_3390_biomimetics8040364 crossref_primary_10_1016_j_mechmachtheory_2022_104936 crossref_primary_10_1016_j_engappai_2025_111888 crossref_primary_10_1109_LRA_2025_3561573 crossref_primary_10_1109_TRO_2019_2958211 crossref_primary_10_1016_j_birob_2025_100255 crossref_primary_10_3390_electronics14071264 crossref_primary_10_1109_LRA_2023_3290509 crossref_primary_10_1007_s12555_024_0666_x crossref_primary_10_1109_LRA_2021_3066833 crossref_primary_10_1109_TRO_2023_3299527 crossref_primary_10_1109_ACCESS_2022_3176608 crossref_primary_10_1109_TVCG_2021_3139031 crossref_primary_10_1146_annurev_control_061523_102310 crossref_primary_10_1007_s43154_021_00059_0 crossref_primary_10_1111_cgf_15175 crossref_primary_10_3390_mi13071055 crossref_primary_10_1109_TNNLS_2020_3016523 crossref_primary_10_1109_LRA_2024_3519908 crossref_primary_10_1109_TRO_2025_3547267 crossref_primary_10_1016_j_ast_2022_107907 crossref_primary_10_3389_frobt_2022_970890 crossref_primary_10_1109_LRA_2020_2972879 crossref_primary_10_1109_TMECH_2023_3277102 crossref_primary_10_1109_LRA_2023_3246839 crossref_primary_10_1016_j_robot_2024_104775 crossref_primary_10_1109_TRO_2021_3078317 crossref_primary_10_1109_TNNLS_2023_3281604 crossref_primary_10_1007_s42235_024_00541_3 crossref_primary_10_1109_ACCESS_2023_3310405 crossref_primary_10_1126_scirobotics_abo0235 crossref_primary_10_3390_robotics14060076 crossref_primary_10_1002_gamm_202100009 crossref_primary_10_3390_aerospace11050395 crossref_primary_10_3390_machines10050292 crossref_primary_10_1007_s12555_022_1218_x crossref_primary_10_1038_s42256_023_00701_w crossref_primary_10_1063_5_0007754 crossref_primary_10_1109_TNNLS_2021_3119127 crossref_primary_10_1109_TASE_2025_3561771 crossref_primary_10_1109_LRA_2023_3323893 crossref_primary_10_1109_TAI_2023_3249683 crossref_primary_10_1038_s42256_024_00861_3 crossref_primary_10_1109_TCYB_2019_2949596 crossref_primary_10_1016_j_rineng_2025_104661 crossref_primary_10_1038_s42256_020_00263_1 crossref_primary_10_1007_s41693_022_00069_0 crossref_primary_10_1038_s41598_024_77779_8 crossref_primary_10_1109_LRA_2025_3569117 crossref_primary_10_1007_s10489_025_06584_1 crossref_primary_10_1016_j_knosys_2023_111101 crossref_primary_10_1109_TRO_2023_3236952 crossref_primary_10_3390_aerospace9110632 crossref_primary_10_1016_j_knosys_2023_111341 crossref_primary_10_1109_LRA_2020_3011379 crossref_primary_10_1016_j_robot_2024_104799 crossref_primary_10_1109_LRA_2023_3286171 crossref_primary_10_3390_app9071508 crossref_primary_10_1109_ACCESS_2022_3148921 crossref_primary_10_3390_biomimetics9060310 crossref_primary_10_1109_LRA_2025_3572427 crossref_primary_10_3390_s21175907 crossref_primary_10_1109_TMECH_2020_2999401 crossref_primary_10_1155_2021_7331894 crossref_primary_10_1109_TNNLS_2021_3112718 crossref_primary_10_1007_s11071_024_09445_7 crossref_primary_10_1515_teme_2019_0072 crossref_primary_10_1051_matecconf_202440604007 crossref_primary_10_1109_ACCESS_2023_3265895 crossref_primary_10_1088_1748_3190_ad839e crossref_primary_10_1016_j_robot_2024_104787 crossref_primary_10_1109_LRA_2022_3194315 crossref_primary_10_1109_TVT_2022_3205452 crossref_primary_10_1126_scirobotics_ade2256 crossref_primary_10_1007_s40747_025_02056_8 crossref_primary_10_1109_TRO_2022_3154715 crossref_primary_10_1109_TRO_2022_3158194 crossref_primary_10_1109_TRO_2024_3400935 crossref_primary_10_1089_soro_2022_0177 crossref_primary_10_1002_aisy_202401059 crossref_primary_10_1016_j_neunet_2023_08_030 crossref_primary_10_1109_TNNLS_2022_3219814 crossref_primary_10_1016_j_jag_2024_103708 crossref_primary_10_1108_RIA_10_2023_0146 crossref_primary_10_1109_ACCESS_2020_2992794 crossref_primary_10_1017_S0263574722000625 crossref_primary_10_1109_ACCESS_2025_3579786 crossref_primary_10_3390_biomimetics10070469 crossref_primary_10_1038_s44182_025_00048_x crossref_primary_10_1109_LRA_2022_3226027 crossref_primary_10_1109_TII_2023_3240758 crossref_primary_10_1038_s44172_023_00089_w crossref_primary_10_1016_j_mechmachtheory_2024_105859 crossref_primary_10_1109_LRA_2022_3184779 crossref_primary_10_1038_s41467_019_13239_6 crossref_primary_10_3390_robotics13080113 crossref_primary_10_1016_j_robot_2023_104468 crossref_primary_10_3390_s23020762 crossref_primary_10_1016_j_compeleceng_2021_107027 crossref_primary_10_1007_s11227_024_05963_8 crossref_primary_10_1038_s41598_023_38259_7 crossref_primary_10_1109_LRA_2025_3527757 crossref_primary_10_1109_TAC_2022_3200948 crossref_primary_10_1016_j_mechmachtheory_2023_105448 crossref_primary_10_1126_scirobotics_adi9579 crossref_primary_10_1146_annurev_control_030323_022510 crossref_primary_10_1109_ACCESS_2023_3317183 crossref_primary_10_1002_aisy_202300172 crossref_primary_10_1109_TPAMI_2024_3443916 crossref_primary_10_1049_csy2_12062 crossref_primary_10_1109_TRO_2022_3181014 crossref_primary_10_1007_s11071_021_06376_5 crossref_primary_10_3390_robotics14050057 crossref_primary_10_1049_csy2_12064 crossref_primary_10_1109_LRA_2024_3398428 crossref_primary_10_1016_j_eswa_2024_124887 crossref_primary_10_1016_j_robot_2022_104150 crossref_primary_10_1007_s11633_023_1429_5 crossref_primary_10_3389_frobt_2022_951293 crossref_primary_10_3389_fenrg_2021_725353 crossref_primary_10_1109_TRO_2024_3434208 crossref_primary_10_1109_TAI_2023_3237665 crossref_primary_10_1002_rob_70035 crossref_primary_10_1016_j_aei_2023_102256 crossref_primary_10_1016_j_jcp_2021_110317 crossref_primary_10_1073_pnas_2213698120 crossref_primary_10_3390_app11041816 crossref_primary_10_1109_ACCESS_2021_3076530 crossref_primary_10_1038_s41598_024_84060_5 crossref_primary_10_3389_fncir_2023_1111285 crossref_primary_10_1016_j_robot_2023_104550 crossref_primary_10_1016_j_robot_2023_104443 crossref_primary_10_1109_MRA_2024_3487322 crossref_primary_10_1109_TCDS_2021_3092715 crossref_primary_10_1002_rob_70028 crossref_primary_10_1088_1748_3190_ac45e6 crossref_primary_10_1016_j_birob_2021_100029 crossref_primary_10_1109_ACCESS_2024_3485506 crossref_primary_10_1109_MRA_2024_3487325 crossref_primary_10_1109_LRA_2024_3418310 crossref_primary_10_1007_s42235_024_00618_z crossref_primary_10_1017_S0263574723001261 crossref_primary_10_1109_TIE_2024_3360604 crossref_primary_10_1016_j_cag_2024_104141 crossref_primary_10_1109_LRA_2020_2974653 crossref_primary_10_1177_02783649241285161 crossref_primary_10_1088_1757_899X_1261_1_012018 crossref_primary_10_1109_TRO_2022_3141602 crossref_primary_10_1016_j_neucom_2025_129363 crossref_primary_10_1126_scirobotics_adi8022 crossref_primary_10_1109_LRA_2024_3483039 crossref_primary_10_1038_s42005_025_02146_6 crossref_primary_10_1109_TAI_2023_3316637 crossref_primary_10_1109_TRO_2021_3106832 crossref_primary_10_1109_ACCESS_2023_3313637 crossref_primary_10_1016_j_neucom_2023_01_016 crossref_primary_10_1177_02783649241312698 crossref_primary_10_1109_LRA_2021_3133934 crossref_primary_10_1038_s41598_025_94163_2 crossref_primary_10_1109_LRA_2021_3068639 crossref_primary_10_3389_frobt_2021_702845 crossref_primary_10_1038_s41598_025_13055_7 crossref_primary_10_1109_LRA_2020_3013848 crossref_primary_10_1155_2022_4194747 crossref_primary_10_1016_j_conengprac_2025_106536 crossref_primary_10_1016_j_techfore_2023_122588 crossref_primary_10_1109_TAES_2022_3207705 crossref_primary_10_1109_LRA_2021_3064284 crossref_primary_10_1007_s42235_019_0050_3 crossref_primary_10_1109_TASE_2023_3345876 crossref_primary_10_3390_s20174911 crossref_primary_10_3389_fncir_2020_00046 crossref_primary_10_1109_TMM_2022_3151463 crossref_primary_10_1088_1748_3190_ace017 crossref_primary_10_1126_scirobotics_aaw3520 crossref_primary_10_1186_s10033_023_00963_w crossref_primary_10_1109_MCS_2020_3019143 crossref_primary_10_1126_scirobotics_abk0395 crossref_primary_10_1109_MRA_2022_3204237 crossref_primary_10_3390_en15062198 crossref_primary_10_1109_LRA_2020_2974685 crossref_primary_10_1177_02783649251364393 crossref_primary_10_1016_j_engappai_2024_109418 crossref_primary_10_1177_10775463241264047 crossref_primary_10_1089_soro_2022_0220 crossref_primary_10_1038_s42256_022_00444_0 crossref_primary_10_3390_math11102234 crossref_primary_10_1016_j_neunet_2021_09_017 crossref_primary_10_1109_ACCESS_2023_3333388 crossref_primary_10_1109_MRA_2020_2980547 crossref_primary_10_1016_j_engappai_2023_106197 crossref_primary_10_1109_ACCESS_2023_3286871 crossref_primary_10_1109_LRA_2022_3143227 crossref_primary_10_1109_MRA_2023_3262461 crossref_primary_10_1016_j_eswa_2024_124310 crossref_primary_10_1016_j_jai_2022_100003 crossref_primary_10_3389_frobt_2023_1223946 crossref_primary_10_1109_TIE_2023_3299051 crossref_primary_10_1109_LRA_2024_3497754 crossref_primary_10_3389_frobt_2022_974537 crossref_primary_10_3389_frobt_2021_697612 crossref_primary_10_1002_adrr_202500036 crossref_primary_10_1109_LRA_2021_3065278 crossref_primary_10_1109_LRA_2022_3145516 crossref_primary_10_34133_cbsystems_0365 crossref_primary_10_1038_s44182_025_00043_2 crossref_primary_10_1017_S0263574722001436 crossref_primary_10_3390_machines10070496 crossref_primary_10_1073_pnas_2017015118 crossref_primary_10_3390_s21020331 crossref_primary_10_1109_TTE_2024_3377809 crossref_primary_10_1177_02783649231169492 crossref_primary_10_1177_0278364920987859 crossref_primary_10_1109_LRA_2024_3375086 crossref_primary_10_3390_electronics13010116 crossref_primary_10_1007_s10846_021_01412_3 crossref_primary_10_1126_scirobotics_abc5986 crossref_primary_10_1007_s10015_022_00776_5 crossref_primary_10_1126_scirobotics_adi7566 crossref_primary_10_1038_s42256_022_00576_3 crossref_primary_10_1002_rob_22292 crossref_primary_10_1109_LRA_2022_3143567 crossref_primary_10_1016_j_heliyon_2024_e37237 crossref_primary_10_3390_robotics13010017 crossref_primary_10_1007_s00521_022_07033_7 crossref_primary_10_3390_app13010154 crossref_primary_10_1088_1755_1315_502_1_012018 crossref_primary_10_1109_LRA_2021_3092647 crossref_primary_10_1007_s11370_021_00360_z crossref_primary_10_1109_TNNLS_2021_3055499 crossref_primary_10_1038_s42256_025_01048_0 crossref_primary_10_3390_aerospace10100834 crossref_primary_10_1109_LRA_2023_3342559 crossref_primary_10_1017_S026357472500044X crossref_primary_10_1038_s42256_025_00988_x crossref_primary_10_1109_TRO_2025_3603551 crossref_primary_10_3390_math11041021 crossref_primary_10_1109_TNNLS_2021_3107742 crossref_primary_10_3390_s21041278 crossref_primary_10_3390_machines10100834 crossref_primary_10_3390_biomimetics9120749 crossref_primary_10_1007_s10489_025_06360_1 crossref_primary_10_3390_robotics11010003 crossref_primary_10_1109_TITS_2021_3066366 crossref_primary_10_1063_5_0097241 crossref_primary_10_3389_frobt_2021_696452 crossref_primary_10_1126_scirobotics_adi9641 crossref_primary_10_1016_j_ins_2022_08_041 crossref_primary_10_1109_LRA_2023_3313923 crossref_primary_10_1109_LRA_2022_3229907 crossref_primary_10_1109_JAS_2023_123375 crossref_primary_10_1007_s12206_023_0838_2 crossref_primary_10_1038_s41586_024_07382_4 crossref_primary_10_1038_s41598_024_79292_4 crossref_primary_10_1109_TRO_2024_3386391 crossref_primary_10_1109_TSMC_2022_3229213 crossref_primary_10_1109_LRA_2023_3307008 crossref_primary_10_1126_scirobotics_adr6125 crossref_primary_10_3390_aerospace9060294 crossref_primary_10_1002_adfm_202304642 crossref_primary_10_1109_TRO_2025_3588452 crossref_primary_10_1016_j_engappai_2025_112079 crossref_primary_10_1038_s41467_024_48670_x crossref_primary_10_1007_s11071_024_10630_x crossref_primary_10_1109_LRA_2022_3151396 crossref_primary_10_1109_LRA_2024_3446287 |
| ContentType | Journal Article |
| Copyright | Copyright © 2019 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. |
| Copyright_xml | – notice: Copyright © 2019 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. |
| DBID | NPM 7X8 |
| DOI | 10.1126/scirobotics.aau5872 |
| DatabaseName | PubMed MEDLINE - Academic |
| DatabaseTitle | PubMed MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2470-9476 |
| ExternalDocumentID | 33137755 |
| Genre | Research Support, Non-U.S. Gov't Journal Article |
| GroupedDBID | 0R~ ABJNI ACGFS AJGZS ALMA_UNASSIGNED_HOLDINGS ARCSS BKF EBS NPM O9- SJN 7X8 |
| ID | FETCH-LOGICAL-c416t-27f156a7e6ea0d5a80f0f68f1ce85bc6927c4287a3371cdc934a78b5721acc7e2 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 948 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000455967100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2470-9476 |
| IngestDate | Thu Oct 02 06:38:35 EDT 2025 Wed Feb 19 02:29:50 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 26 |
| Language | English |
| License | Copyright © 2019 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c416t-27f156a7e6ea0d5a80f0f68f1ce85bc6927c4287a3371cdc934a78b5721acc7e2 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0003-3856-0735 0000-0002-4285-4990 0000-0002-3444-8079 0000-0003-3428-8455 0000-0003-1851-0976 0000-0002-5072-7385 0000-0003-0858-0970 |
| OpenAccessLink | http://infoscience.epfl.ch/record/265881 |
| PMID | 33137755 |
| PQID | 2457282606 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2457282606 pubmed_primary_33137755 |
| PublicationCentury | 2000 |
| PublicationDate | 2019-01-16 |
| PublicationDateYYYYMMDD | 2019-01-16 |
| PublicationDate_xml | – month: 01 year: 2019 text: 2019-01-16 day: 16 |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Science robotics |
| PublicationTitleAlternate | Sci Robot |
| PublicationYear | 2019 |
| SSID | ssj0001763642 |
| Score | 2.6326478 |
| Snippet | Legged robots pose one of the greatest challenges in robotics. Dynamic and agile maneuvers of animals cannot be imitated by existing methods that are crafted... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| Title | Learning agile and dynamic motor skills for legged robots |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/33137755 https://www.proquest.com/docview/2457282606 |
| Volume | 4 |
| WOSCitedRecordID | wos000455967100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELaAMsDA-1FeMhKrIYkT25kQQlQsVB1A6hZd_IgQVVKalt_POUlVFiQkliiLlfh8vnx3vnwfITe5cInMA8VUCimL_R1w65jB3Bm0iSAJoRGbkMOhGo_TUVdwq7u2ymVMbAK1qbSvkd9FcSIxPUC8fT_9ZF41yp-udhIa66THEcr4li45VqsaC24e0ejnRLEMWBpL0REPdf_NzKq88mzItwCLRDUswb_AzOZzM9j974vukZ0OaNKH1jP2yZotD8j2D_rBQ5J25KoFhQKDA4XSUNMq1FNcwWpG64_3yaSmCGzpxBaFNbSZS31E3gZPr4_PrJNSYBoR15xF0mGiBtIKC4FJQAUucEK50KuW5lqkkdQ-eQLOZaiNTnkMUuU4kxC0ljY6JhtlVdpTQsMoT0EKKXKuYnA4xEWG60DjAxD-QZ9cL-2Soav68wcobbWos5Vl-uSkNW42bTk1Ms499WGSnP1h9DnZQtji27xYKC5Iz-FGtZdkU3_N3-vZVeMDeB2OXr4Bb_e8pA |
| linkProvider | ProQuest |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Learning+agile+and+dynamic+motor+skills+for+legged+robots&rft.jtitle=Science+robotics&rft.au=Hwangbo%2C+Jemin&rft.au=Lee%2C+Joonho&rft.au=Dosovitskiy%2C+Alexey&rft.au=Bellicoso%2C+Dario&rft.date=2019-01-16&rft.eissn=2470-9476&rft.volume=4&rft.issue=26&rft_id=info:doi/10.1126%2Fscirobotics.aau5872&rft_id=info%3Apmid%2F33137755&rft_id=info%3Apmid%2F33137755&rft.externalDocID=33137755 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2470-9476&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2470-9476&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2470-9476&client=summon |