A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-Based Variational Autoencoder

The detection of anomalous executions is valuable for reducing potential hazards in assistive manipulation. Multimodal sensory signals can be helpful for detecting a wide range of anomalies. However, the fusion of high-dimensional and heterogeneous modalities is a challenging problem for model-based...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE robotics and automation letters Vol. 3; no. 3; pp. 1544 - 1551
Main Authors:	Daehyung Park, Hoshi, Yuuna, Kemp, Charles C.
Format:	Journal Article
Language:	English
Published:	Piscataway IEEE 01.07.2018 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Anomalies Anomaly detection assistive robots Decoding deep learning in robotics and automation Detectors Failure detection and recovery Gaussian distribution Hazards Hidden Markov models Robot sensing systems Robots Sensors
ISSN:	2377-3766, 2377-3766
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	The detection of anomalous executions is valuable for reducing potential hazards in assistive manipulation. Multimodal sensory signals can be helpful for detecting a wide range of anomalies. However, the fusion of high-dimensional and heterogeneous modalities is a challenging problem for model-based anomaly detection. We introduce a long short-term memory-based variational autoencoder (LSTM-VAE) that fuses signals and reconstructs their expected distribution by introducing a progress-based varying prior. Our LSTM-VAE-based detector reports an anomaly when a reconstruction-based anomaly score is higher than a state-based threshold. For evaluations with 1555 robot-assisted feeding executions, including 12 representative types of anomalies, our detector had a higher area under the receiver operating characteristic curve of 0.8710 than 5 other baseline detectors from the literature. We also show the variational autoencoding and state-based thresholding are effective in detecting anomalies from 17 raw sensory signals without significant feature engineering effort.
AbstractList	The detection of anomalous executions is valuable for reducing potential hazards in assistive manipulation. Multimodal sensory signals can be helpful for detecting a wide range of anomalies. However, the fusion of high-dimensional and heterogeneous modalities is a challenging problem for model-based anomaly detection. We introduce a long short-term memory-based variational autoencoder (LSTM-VAE) that fuses signals and reconstructs their expected distribution by introducing a progress-based varying prior. Our LSTM-VAE-based detector reports an anomaly when a reconstruction-based anomaly score is higher than a state-based threshold. For evaluations with 1555 robot-assisted feeding executions, including 12 representative types of anomalies, our detector had a higher area under the receiver operating characteristic curve of 0.8710 than 5 other baseline detectors from the literature. We also show the variational autoencoding and state-based thresholding are effective in detecting anomalies from 17 raw sensory signals without significant feature engineering effort.
Author	Daehyung Park Kemp, Charles C. Hoshi, Yuuna
Author_xml	– sequence: 1 surname: Daehyung Park fullname: Daehyung Park email: deric.park@gatech.edu organization: Healthcare Robot. Lab., Georgia Inst. of Technol., Atlanta, GA, USA – sequence: 2 givenname: Yuuna surname: Hoshi fullname: Hoshi, Yuuna email: youna.hoshi@gmail.com organization: Healthcare Robot. Lab., Georgia Inst. of Technol., Atlanta, GA, USA – sequence: 3 givenname: Charles C. surname: Kemp fullname: Kemp, Charles C. email: charlie.kemp@bme.gatech.edu organization: Healthcare Robot. Lab., Georgia Inst. of Technol., Atlanta, GA, USA
BookMark	eNp9UE1Lw0AQXaSCtfYueAl4Tt2vZLPHWK0KLUJtvYbNZiJb0mzd3R76701sEfHgYT5g5r158y7RoLUtIHRN8IQQLO_my3xCMckmNMOEi-QMDSkTImYiTQe_-gs09n6DMSYJFUwmQ1Tl0WLfBLO1lWqivLVb1RyiBwigg3VR3cXSljbEuffGB6iiGUBl2o9o7fus2mj-tlrE98p3s3fljArGtj3XPlhota3AXaHzWjUexqc6QuvZ42r6HM9fn16m-TzWVNAQCw1AaiYhlZwLzSSBRCS8ZDxNMsJqAJ7ikmohSo1rWTFGcMYqrkvBWSIIG6HbI-_O2c89-FBs7N51YnxBqZRM0IT1W_i4pZ313kFd7JzZKncoCC56O4vOzqK3szjZ2UHSPxBtwvejwSnT_Ae8OQINAPzcyaiQvNPyBfAggmo
CODEN	IRALC6
CitedBy_id	crossref_primary_10_3233_JIFS_224416 crossref_primary_10_1016_j_knosys_2023_110936 crossref_primary_10_3390_s25061849 crossref_primary_10_1007_s11227_024_06694_6 crossref_primary_10_3390_app15052861 crossref_primary_10_1016_j_jii_2023_100490 crossref_primary_10_1109_TNSE_2025_3555764 crossref_primary_10_1088_2631_7990_adbd98 crossref_primary_10_1016_j_buildenv_2020_107212 crossref_primary_10_1016_j_cose_2022_102652 crossref_primary_10_1007_s11760_025_04305_2 crossref_primary_10_3389_frobt_2020_578805 crossref_primary_10_1016_j_inffus_2024_102906 crossref_primary_10_1016_j_ress_2023_109404 crossref_primary_10_1016_j_neucom_2025_130611 crossref_primary_10_3390_e27090939 crossref_primary_10_1016_j_ymssp_2025_112863 crossref_primary_10_3390_en16207156 crossref_primary_10_1016_j_knosys_2024_112167 crossref_primary_10_1109_TAES_2024_3463629 crossref_primary_10_3390_drones9060408 crossref_primary_10_1109_ACCESS_2022_3165977 crossref_primary_10_3390_s24020637 crossref_primary_10_1007_s11227_023_05503_w crossref_primary_10_1007_s10489_022_03829_1 crossref_primary_10_1109_JIOT_2024_3401101 crossref_primary_10_3390_e23111466 crossref_primary_10_1016_j_psep_2023_02_078 crossref_primary_10_1109_TETC_2021_3073017 crossref_primary_10_1016_j_ress_2023_109410 crossref_primary_10_1109_TIM_2023_3236354 crossref_primary_10_1109_TNSM_2023_3293806 crossref_primary_10_7595_management_fon_2020_0002 crossref_primary_10_1007_s40998_024_00758_2 crossref_primary_10_1088_1742_6596_2132_1_012012 crossref_primary_10_1016_j_engappai_2023_106466 crossref_primary_10_1109_ACCESS_2023_3289068 crossref_primary_10_3390_app11135869 crossref_primary_10_3390_app14219820 crossref_primary_10_1088_2632_2153_ace756 crossref_primary_10_1177_1748006X211001979 crossref_primary_10_1016_j_compind_2024_104097 crossref_primary_10_1109_TIFS_2025_3561672 crossref_primary_10_1109_ACCESS_2019_2933602 crossref_primary_10_3390_s24092833 crossref_primary_10_3390_s25185686 crossref_primary_10_1109_TIM_2023_3320734 crossref_primary_10_1016_j_engappai_2025_112269 crossref_primary_10_1016_j_eswa_2023_120725 crossref_primary_10_1109_TIM_2024_3449958 crossref_primary_10_1016_j_neunet_2023_12_023 crossref_primary_10_3390_app11199290 crossref_primary_10_1007_s10618_022_00876_7 crossref_primary_10_1007_s10489_021_02527_8 crossref_primary_10_1145_3572780 crossref_primary_10_1007_s10618_020_00697_6 crossref_primary_10_1016_j_engappai_2023_106597 crossref_primary_10_3390_electronics14091857 crossref_primary_10_1109_ACCESS_2023_3313448 crossref_primary_10_1007_s44267_025_00085_y crossref_primary_10_3390_s23229272 crossref_primary_10_3390_s24092845 crossref_primary_10_3390_app13031778 crossref_primary_10_1016_j_cherd_2025_07_041 crossref_primary_10_1016_j_knosys_2025_114511 crossref_primary_10_1016_j_ins_2025_122279 crossref_primary_10_3390_s24041330 crossref_primary_10_1109_JSEN_2024_3452088 crossref_primary_10_1109_TCE_2024_3409391 crossref_primary_10_3390_s24051495 crossref_primary_10_1109_TII_2024_3413952 crossref_primary_10_1016_j_ymssp_2024_111141 crossref_primary_10_1145_3453155 crossref_primary_10_3390_electronics13010195 crossref_primary_10_1109_ACCESS_2022_3164439 crossref_primary_10_1016_j_measurement_2022_111318 crossref_primary_10_1016_j_asoc_2025_113903 crossref_primary_10_32604_cmc_2023_038551 crossref_primary_10_1109_TKDE_2023_3328882 crossref_primary_10_1016_j_eswa_2023_120542 crossref_primary_10_1016_j_asoc_2023_110911 crossref_primary_10_1016_j_artmed_2022_102387 crossref_primary_10_3390_s25103249 crossref_primary_10_1016_j_knosys_2023_110725 crossref_primary_10_1145_3659058 crossref_primary_10_1016_j_cose_2025_104509 crossref_primary_10_3390_electronics12020354 crossref_primary_10_1145_3592790 crossref_primary_10_1109_TNSM_2024_3486167 crossref_primary_10_1109_LRA_2022_3153989 crossref_primary_10_1109_JBHI_2021_3101549 crossref_primary_10_1093_bib_bbz170 crossref_primary_10_1016_j_ins_2022_07_179 crossref_primary_10_1016_j_isatra_2022_09_009 crossref_primary_10_1016_j_ins_2024_120852 crossref_primary_10_1109_TETCI_2023_3290027 crossref_primary_10_1007_s10010_021_00481_y crossref_primary_10_1007_s11760_024_03543_0 crossref_primary_10_3390_s25113396 crossref_primary_10_1016_j_eswa_2025_126667 crossref_primary_10_1002_int_23027 crossref_primary_10_1016_j_engappai_2023_107510 crossref_primary_10_1016_j_procir_2021_11_076 crossref_primary_10_1016_j_idm_2025_08_006 crossref_primary_10_1007_s10994_024_06689_7 crossref_primary_10_1109_ACCESS_2025_3594473 crossref_primary_10_1109_JSYST_2023_3347435 crossref_primary_10_1109_TPAMI_2024_3443141 crossref_primary_10_3390_a15110429 crossref_primary_10_3390_electronics13071326 crossref_primary_10_1016_j_ress_2023_109306 crossref_primary_10_1016_j_knosys_2019_105187 crossref_primary_10_1007_s40747_025_01839_3 crossref_primary_10_1093_comjnl_bxaa174 crossref_primary_10_3390_s22082886 crossref_primary_10_1016_j_asoc_2024_111426 crossref_primary_10_3233_AIC_200629 crossref_primary_10_1109_JIOT_2024_3390691 crossref_primary_10_3390_s22166249 crossref_primary_10_1109_ACCESS_2024_3513001 crossref_primary_10_1109_ACCESS_2023_3301140 crossref_primary_10_1109_TIM_2024_3460930 crossref_primary_10_1145_3663573 crossref_primary_10_1016_j_ipm_2023_103383 crossref_primary_10_1016_j_measen_2024_101157 crossref_primary_10_3390_app15063234 crossref_primary_10_1109_TRO_2023_3332224 crossref_primary_10_1109_TNNLS_2021_3105827 crossref_primary_10_1016_j_jmsy_2024_09_021 crossref_primary_10_1016_j_future_2024_107545 crossref_primary_10_1109_TIM_2025_3577826 crossref_primary_10_1007_s10489_025_06589_w crossref_primary_10_1109_JIOT_2024_3421577 crossref_primary_10_1109_TGRS_2020_2984951 crossref_primary_10_1016_j_jnca_2023_103648 crossref_primary_10_1016_j_engappai_2025_111310 crossref_primary_10_1016_j_jfoodeng_2025_112485 crossref_primary_10_1109_TETC_2023_3280577 crossref_primary_10_1016_j_neucom_2023_126644 crossref_primary_10_3390_s25175216 crossref_primary_10_1016_j_asoc_2023_110832 crossref_primary_10_1016_j_asoc_2022_108489 crossref_primary_10_1186_s13677_024_00677_x crossref_primary_10_1016_j_knosys_2024_111912 crossref_primary_10_1016_j_future_2023_03_020 crossref_primary_10_3390_s20061670 crossref_primary_10_1080_19475705_2025_2519429 crossref_primary_10_3390_app14020774 crossref_primary_10_1016_j_psep_2022_05_039 crossref_primary_10_3390_bioengineering10121348 crossref_primary_10_3390_rs16132415 crossref_primary_10_1109_TIM_2025_3593530 crossref_primary_10_1016_j_yofte_2024_103969 crossref_primary_10_1109_LRA_2023_3346270 crossref_primary_10_1016_j_jgsce_2024_205394 crossref_primary_10_1016_j_procs_2021_08_005 crossref_primary_10_1016_j_eswa_2024_126156 crossref_primary_10_1016_j_eswa_2025_126573 crossref_primary_10_3139_104_112276 crossref_primary_10_1016_j_neucom_2022_03_048 crossref_primary_10_1007_s12083_024_01712_z crossref_primary_10_1016_j_conengprac_2023_105531 crossref_primary_10_1109_LRA_2020_3038377 crossref_primary_10_3390_s23177552 crossref_primary_10_32604_cmc_2023_044253 crossref_primary_10_1016_j_inffus_2025_103462 crossref_primary_10_1109_LRA_2025_3583161 crossref_primary_10_1109_ACCESS_2021_3097116 crossref_primary_10_3390_s24051522 crossref_primary_10_3390_signals2040042 crossref_primary_10_3390_s20226467 crossref_primary_10_1109_LRA_2022_3192794 crossref_primary_10_1109_TASE_2025_3538328 crossref_primary_10_1016_j_jlp_2021_104623 crossref_primary_10_1016_j_cose_2024_103813 crossref_primary_10_1016_j_petrol_2022_110522 crossref_primary_10_1109_TIM_2023_3315420 crossref_primary_10_1016_j_nucengdes_2025_113956 crossref_primary_10_1007_s44443_025_00024_3 crossref_primary_10_1016_j_measurement_2025_118905 crossref_primary_10_3233_JIFS_222554 crossref_primary_10_1109_TSC_2024_3411481 crossref_primary_10_1016_j_cose_2024_103825 crossref_primary_10_26599_TST_2023_9010073 crossref_primary_10_1016_j_cie_2022_108559 crossref_primary_10_1016_j_compag_2025_110566 crossref_primary_10_1016_j_inffus_2022_08_011 crossref_primary_10_1109_ACCESS_2021_3107975 crossref_primary_10_1177_09287329251342392 crossref_primary_10_1109_TASE_2024_3452149 crossref_primary_10_3390_aerospace9080437 crossref_primary_10_1016_j_neunet_2025_107664 crossref_primary_10_1016_j_robot_2019_103344 crossref_primary_10_1016_j_neucom_2021_03_062 crossref_primary_10_1002_sdtp_18143 crossref_primary_10_1016_j_epsr_2020_106253 crossref_primary_10_1109_JIOT_2023_3289814 crossref_primary_10_1007_s11227_025_07044_w crossref_primary_10_1016_j_is_2024_102429 crossref_primary_10_1109_TNNLS_2023_3325667 crossref_primary_10_1016_j_isatra_2024_06_025 crossref_primary_10_1002_eng2_13021 crossref_primary_10_1061_JENMDT_EMENG_7635 crossref_primary_10_1007_s13042_024_02212_5 crossref_primary_10_3390_s25010190 crossref_primary_10_1109_TIFS_2024_3459631 crossref_primary_10_1109_ACCESS_2023_3276297 crossref_primary_10_1007_s11554_024_01459_z crossref_primary_10_1016_j_patcog_2022_109084 crossref_primary_10_3390_s22093468 crossref_primary_10_1007_s10489_025_06650_8 crossref_primary_10_1109_ACCESS_2021_3078553 crossref_primary_10_1109_TII_2024_3485808 crossref_primary_10_1109_ACCESS_2020_3000859 crossref_primary_10_1007_s11370_021_00355_w crossref_primary_10_1007_s10489_023_04764_5 crossref_primary_10_1109_TIM_2024_3369159 crossref_primary_10_1002_cend_202400053 crossref_primary_10_1038_s41598_023_31193_8 crossref_primary_10_1007_s10618_022_00911_7 crossref_primary_10_1109_TIFS_2025_3588674 crossref_primary_10_1109_TNNLS_2023_3262277 crossref_primary_10_1016_j_knosys_2024_111928 crossref_primary_10_1016_j_psep_2025_107066 crossref_primary_10_1109_TKDE_2023_3335317 crossref_primary_10_1007_s11063_020_10223_w crossref_primary_10_1007_s10846_021_01496_x crossref_primary_10_3390_s23052844 crossref_primary_10_1109_LRA_2021_3062597 crossref_primary_10_1016_j_cose_2023_103310 crossref_primary_10_3233_IDA_195075 crossref_primary_10_1002_stc_2948 crossref_primary_10_3390_aerospace7080115 crossref_primary_10_1016_j_future_2025_107751 crossref_primary_10_1109_ACCESS_2022_3147188 crossref_primary_10_3390_drones7050326 crossref_primary_10_1016_j_engappai_2025_111308 crossref_primary_10_1016_j_apor_2021_103030 crossref_primary_10_1109_JIOT_2025_3583424 crossref_primary_10_1016_j_knosys_2024_111507 crossref_primary_10_1016_j_comnet_2025_111729 crossref_primary_10_1016_j_cose_2023_103581 crossref_primary_10_1007_s10846_021_01312_6 crossref_primary_10_3390_math13071209 crossref_primary_10_1109_MGRS_2018_2853555 crossref_primary_10_1109_ACCESS_2024_3359413 crossref_primary_10_32604_cmc_2022_023641 crossref_primary_10_1007_s42979_021_00658_w crossref_primary_10_1016_j_jksuci_2024_102232 crossref_primary_10_3390_electronics14102068 crossref_primary_10_1016_j_eswa_2025_127379 crossref_primary_10_1016_j_measurement_2022_112171 crossref_primary_10_1016_j_neucom_2025_131385 crossref_primary_10_1007_s00170_023_11617_5 crossref_primary_10_1109_ACCESS_2022_3178592 crossref_primary_10_1109_ACCESS_2021_3064854 crossref_primary_10_1016_j_jnca_2025_104216 crossref_primary_10_1109_TRO_2024_3468768 crossref_primary_10_1007_s00521_023_08213_9 crossref_primary_10_1109_TNNLS_2023_3337876 crossref_primary_10_4018_IJISP_343306 crossref_primary_10_1109_TIM_2024_3440379 crossref_primary_10_1016_j_nucengdes_2024_112949 crossref_primary_10_1080_0951192X_2025_2452985 crossref_primary_10_1016_j_patcog_2024_110874 crossref_primary_10_1016_j_psep_2021_10_036 crossref_primary_10_1109_JIOT_2025_3558273 crossref_primary_10_32604_cmc_2024_053765 crossref_primary_10_1109_LRA_2025_3601037 crossref_primary_10_1007_s10489_025_06441_1 crossref_primary_10_1109_TR_2025_3528256 crossref_primary_10_1109_TIM_2020_2994012 crossref_primary_10_1007_s10489_025_06551_w crossref_primary_10_1007_s10618_023_00988_8 crossref_primary_10_1109_TII_2024_3381790 crossref_primary_10_1080_09540091_2022_2078281 crossref_primary_10_3390_s20133738 crossref_primary_10_1016_j_neunet_2024_106638 crossref_primary_10_1109_ACCESS_2021_3094243 crossref_primary_10_1016_j_ins_2024_120222 crossref_primary_10_3390_app122010390 crossref_primary_10_1109_TKDE_2024_3360640 crossref_primary_10_1109_JIOT_2023_3303946 crossref_primary_10_1080_03088839_2024_2388177 crossref_primary_10_1109_TC_2021_3065073 crossref_primary_10_1016_j_future_2023_02_015 crossref_primary_10_1016_j_robot_2022_104067 crossref_primary_10_1007_s00530_024_01472_z crossref_primary_10_1109_JIOT_2021_3100509 crossref_primary_10_1109_JSEN_2024_3509632 crossref_primary_10_1109_ACCESS_2024_3497755 crossref_primary_10_1109_JSTARS_2020_2964409 crossref_primary_10_1016_j_isatra_2023_09_002 crossref_primary_10_1109_TNNLS_2022_3162949 crossref_primary_10_1016_j_conengprac_2024_106164 crossref_primary_10_1145_3702978 crossref_primary_10_1049_csy2_12085 crossref_primary_10_3390_s25144358 crossref_primary_10_1016_j_jfoodeng_2024_111996 crossref_primary_10_1109_TII_2024_3393528 crossref_primary_10_1109_TAES_2024_3456748 crossref_primary_10_1007_s11227_023_05772_5 crossref_primary_10_1109_JIOT_2025_3577931 crossref_primary_10_1016_j_engappai_2024_109323 crossref_primary_10_1016_j_engappai_2024_109687 crossref_primary_10_3390_math11051204 crossref_primary_10_1016_j_jhydrol_2021_127221 crossref_primary_10_1109_JIOT_2025_3537864 crossref_primary_10_1016_j_is_2025_102524 crossref_primary_10_1002_cite_202200238 crossref_primary_10_1088_1361_6501_ad9495 crossref_primary_10_1109_ACCESS_2022_3216930 crossref_primary_10_3390_s23156660 crossref_primary_10_1016_j_patcog_2022_108945 crossref_primary_10_1109_JAS_2023_123423 crossref_primary_10_1016_j_inffus_2024_102255 crossref_primary_10_1007_s10489_022_04324_3 crossref_primary_10_3390_electronics14010065 crossref_primary_10_1016_j_rineng_2025_106801 crossref_primary_10_1371_journal_pone_0324543 crossref_primary_10_1145_3691338 crossref_primary_10_1109_TCE_2024_3376440 crossref_primary_10_1007_s10489_025_06606_y crossref_primary_10_1080_01691864_2022_2035253 crossref_primary_10_1007_s10844_025_00918_8 crossref_primary_10_1007_s10489_022_04337_y crossref_primary_10_1016_j_measurement_2021_109529 crossref_primary_10_1109_TGRS_2022_3155969 crossref_primary_10_3390_s24196414 crossref_primary_10_1109_LRA_2023_3250008 crossref_primary_10_1155_2022_4222827 crossref_primary_10_1109_JIOT_2023_3323620 crossref_primary_10_1002_cpe_70245 crossref_primary_10_1016_j_jfoodeng_2023_111448 crossref_primary_10_3390_electronics11233955 crossref_primary_10_1016_j_jmsy_2024_06_006 crossref_primary_10_1007_s11370_021_00398_z crossref_primary_10_1016_j_knosys_2023_111002 crossref_primary_10_3390_electronics12132763 crossref_primary_10_1515_auto_2023_0031 crossref_primary_10_1109_JIOT_2024_3520362 crossref_primary_10_1007_s00521_021_06017_3 crossref_primary_10_1016_j_jhydrol_2022_128127 crossref_primary_10_1016_j_anucene_2020_108077 crossref_primary_10_1016_j_measurement_2020_107890 crossref_primary_10_1016_j_aei_2024_102357 crossref_primary_10_1016_j_neucom_2024_128428 crossref_primary_10_1109_JSEN_2020_2995271 crossref_primary_10_3390_electronics14071401 crossref_primary_10_1109_ACCESS_2025_3549402 crossref_primary_10_1109_JSEN_2024_3452955 crossref_primary_10_1109_TKDE_2024_3466291 crossref_primary_10_1109_LRA_2021_3074084 crossref_primary_10_1002_2050_7038_12103 crossref_primary_10_3390_math12243969 crossref_primary_10_1016_j_asr_2024_09_050 crossref_primary_10_1016_j_jmsy_2025_07_002 crossref_primary_10_1016_j_patcog_2024_110826 crossref_primary_10_1016_j_aei_2025_103620 crossref_primary_10_1109_JPROC_2021_3052449 crossref_primary_10_1109_JIOT_2024_3443910 crossref_primary_10_1177_02783649241297998 crossref_primary_10_1007_s13042_024_02482_z crossref_primary_10_1016_j_engappai_2024_108663 crossref_primary_10_1109_JIOT_2024_3414492 crossref_primary_10_3233_JIFS_200175 crossref_primary_10_1007_s10462_025_11108_x crossref_primary_10_1016_j_eswa_2025_129049 crossref_primary_10_1016_j_jfranklin_2024_107199 crossref_primary_10_1109_JSEN_2021_3105226 crossref_primary_10_1109_TII_2023_3288226 crossref_primary_10_1109_TIM_2022_3223142 crossref_primary_10_1016_j_asoc_2022_109903 crossref_primary_10_1109_ACCESS_2024_3522325 crossref_primary_10_1109_TII_2022_3231923 crossref_primary_10_1007_s10618_023_00985_x crossref_primary_10_1109_TNNLS_2024_3439404 crossref_primary_10_1007_s13369_025_10300_z crossref_primary_10_1016_j_psep_2024_04_012 crossref_primary_10_3390_ai6090215 crossref_primary_10_3390_app15105623 crossref_primary_10_1109_ACCESS_2022_3167640 crossref_primary_10_1121_10_0034831 crossref_primary_10_3390_electronics13112032 crossref_primary_10_1080_08839514_2025_2538519 crossref_primary_10_1016_j_jfoodeng_2025_112818 crossref_primary_10_1016_j_future_2025_108126 crossref_primary_10_1109_TKDE_2024_3475809 crossref_primary_10_1371_journal_pone_0286770 crossref_primary_10_1007_s10115_024_02107_5 crossref_primary_10_1016_j_ijcip_2023_100612 crossref_primary_10_1038_s41598_024_51374_3 crossref_primary_10_1016_j_engappai_2024_108684 crossref_primary_10_1007_s11227_025_07455_9 crossref_primary_10_1109_TON_2025_3540091 crossref_primary_10_1016_j_jobe_2023_107605 crossref_primary_10_1080_00207543_2023_2175591 crossref_primary_10_1007_s42417_025_01814_9 crossref_primary_10_1109_TVT_2023_3285599 crossref_primary_10_1016_j_eswa_2024_124348 crossref_primary_10_1007_s11036_023_02204_9 crossref_primary_10_3390_electronics12194146 crossref_primary_10_1109_JSEN_2023_3327138 crossref_primary_10_1016_j_eswa_2023_120818 crossref_primary_10_1109_JIOT_2023_3262612 crossref_primary_10_1177_14759217251369727 crossref_primary_10_1016_j_asoc_2023_111169 crossref_primary_10_1080_01969722_2023_2240651 crossref_primary_10_1109_TIM_2024_3493890 crossref_primary_10_3390_s24020569 crossref_primary_10_1016_j_istruc_2025_109092 crossref_primary_10_1109_ACCESS_2024_3415088 crossref_primary_10_1007_s00530_023_01199_3 crossref_primary_10_1109_ACCESS_2023_3289921 crossref_primary_10_1016_j_dsp_2024_104518 crossref_primary_10_1109_TNSM_2019_2919327 crossref_primary_10_1016_j_asoc_2025_113761 crossref_primary_10_1016_j_cose_2025_104461 crossref_primary_10_1177_00368504211021192 crossref_primary_10_1186_s13677_025_00766_5 crossref_primary_10_1007_s11227_023_05534_3 crossref_primary_10_1109_TASE_2020_3042158 crossref_primary_10_1109_ACCESS_2019_2895394 crossref_primary_10_1016_j_amar_2022_100212 crossref_primary_10_1109_TNSRE_2023_3328888 crossref_primary_10_1177_16878140211013138 crossref_primary_10_1016_j_compag_2023_108252 crossref_primary_10_3390_electronics11152306 crossref_primary_10_1109_JSEN_2025_3530007 crossref_primary_10_1007_s00500_023_08467_4 crossref_primary_10_1109_JSAC_2022_3191341 crossref_primary_10_1002_rob_22156 crossref_primary_10_1109_JIOT_2024_3414304 crossref_primary_10_1109_TIM_2024_3398110 crossref_primary_10_3390_app121910078 crossref_primary_10_1016_j_neunet_2023_11_023 crossref_primary_10_1007_s10489_025_06481_7 crossref_primary_10_1109_ACCESS_2022_3213038 crossref_primary_10_3390_e23010083 crossref_primary_10_3390_s25020310 crossref_primary_10_3390_s23031104 crossref_primary_10_1109_TGRS_2020_3019313 crossref_primary_10_1016_j_psep_2024_04_052 crossref_primary_10_1109_ACCESS_2024_3371891 crossref_primary_10_1016_j_compind_2023_104024 crossref_primary_10_1016_j_ress_2018_11_027 crossref_primary_10_1109_TII_2022_3216006 crossref_primary_10_3390_s23104764 crossref_primary_10_1016_j_ress_2023_109717 crossref_primary_10_1109_TCC_2024_3466174 crossref_primary_10_1109_JIOT_2024_3448429 crossref_primary_10_1016_j_neucom_2025_129887 crossref_primary_10_1007_s11063_021_10610_x crossref_primary_10_1016_j_measurement_2025_117497
Cites_doi	10.1145/1390156.1390294 10.1007/s10846-013-0014-5 10.18653/v1/K16-1002 10.1162/neco.1997.9.8.1735 10.15607/RSS.2015.XI.044 10.1109/HSI.2008.4581481 10.1109/ICRA.2015.7139892 10.1109/ICRA.2012.6225358 10.1109/ICRA.2016.7487160 10.1109/COASE.2010.5584452 10.1177/0278364912471865 10.1109/TR.2017.2715180 10.1137/1.9781611972818.1 10.3115/v1/D14-1179 10.1016/j.robot.2014.03.003 10.1109/TASE.2014.2378150 10.1126/science.1127647 10.1109/IJCNN.2017.7966273 10.1145/1541880.1541882 10.1109/IROS.2011.6095100 10.1109/MRA.2012.2229950 10.1109/DSAA.2015.7344872 10.1109/IROS.2014.6943078
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/LRA.2018.2801475
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2377-3766
EndPage	1551
ExternalDocumentID	10_1109_LRA_2018_2801475 8279425
Genre	orig-research
GrantInformation_xml	– fundername: NIDILRR grantid: 90RE5016-01-00 – fundername: Google Faculty Research Award – fundername: NSF grantid: IIS-1150157
GroupedDBID	0R~ 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFS AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE IPLJI JAVBF KQ8 M43 M~E O9- OCL RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c272t-7cee1f39e69447c391e5754b3465813fee460b2c77bc0f9d331083d4cb7435713
IEDL.DBID	RIE
ISSN	2377-3766
IngestDate	Sun Nov 09 08:13:12 EST 2025 Tue Nov 18 21:40:01 EST 2025 Sat Nov 29 06:03:00 EST 2025 Wed Aug 27 02:48:45 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	3
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c272t-7cee1f39e69447c391e5754b3465813fee460b2c77bc0f9d331083d4cb7435713
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-1287-9433 0000-0003-4720-1136 0000-0002-2448-2310
PQID	2299372531
PQPubID	4437225
PageCount	8
ParticipantIDs	crossref_primary_10_1109_LRA_2018_2801475 proquest_journals_2299372531 ieee_primary_8279425 crossref_citationtrail_10_1109_LRA_2018_2801475
PublicationCentury	2000
PublicationDate	2018-07-01
PublicationDateYYYYMMDD	2018-07-01
PublicationDate_xml	– month: 07 year: 2018 text: 2018-07-01 day: 01
PublicationDecade	2010
PublicationPlace	Piscataway
PublicationPlace_xml	– name: Piscataway
PublicationTitle	IEEE robotics and automation letters
PublicationTitleAbbrev	LRA
PublicationYear	2018
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref35 ref13 ref12 ref15 ref14 chollet (ref32) 2015 malhotra (ref23) 0 hinton (ref17) 2006; 313 ref33 ref11 ref10 ref2 ref16 ref19 ref18 karl (ref31) 2017 bayer (ref27) 2014 park (ref4) 0 im (ref30) 0 sölch (ref28) 2016 ref24 ref25 malhotra (ref22) 0 park (ref34) 0 ref21 o'shea (ref20) 2016 ref29 ref8 ref7 ref9 park (ref1) 0 ref3 ref6 ref5 kingma (ref26) 2014 an (ref36) 2015
References_xml	– start-page: 2059 year: 0 ident: ref30 article-title: Denoising criterion for variational auto-encoding framework publication-title: Proc AAAI – ident: ref5 doi: 10.1145/1390156.1390294 – ident: ref12 doi: 10.1007/s10846-013-0014-5 – ident: ref29 doi: 10.18653/v1/K16-1002 – ident: ref19 doi: 10.1162/neco.1997.9.8.1735 – ident: ref9 doi: 10.15607/RSS.2015.XI.044 – year: 2017 ident: ref31 article-title: Deep variational Bayes filters: Unsupervised learning of state space models from raw data publication-title: Proc Int Conf Learn Represent – year: 2014 ident: ref27 article-title: Learning stochastic recurrent networks publication-title: Proc NIPS 2014 Workshop Advances Variational Inf – ident: ref35 doi: 10.1109/HSI.2008.4581481 – ident: ref14 doi: 10.1109/ICRA.2015.7139892 – year: 2015 ident: ref36 article-title: Variational autoencoder based anomaly detection using reconstruction probability – ident: ref15 doi: 10.1109/ICRA.2012.6225358 – ident: ref3 doi: 10.1109/ICRA.2016.7487160 – year: 2016 ident: ref20 article-title: Recurrent neural radio anomaly detection publication-title: arXiv 1611 00301 – year: 2014 ident: ref26 article-title: Auto-encoding variational Bayes publication-title: Proc Int Conf Learn Represent – year: 2016 ident: ref28 article-title: Variational inference for on-line anomaly detection in high-dimensional time series publication-title: Proc ICML 2016 Anomaly Detection Workshop – ident: ref10 doi: 10.1109/COASE.2010.5584452 – ident: ref33 doi: 10.1177/0278364912471865 – start-page: 5406 year: 0 ident: ref34 article-title: Multimodal execution monitoring for robot-assisted feeding publication-title: Proc IEEE/RSJ Int Conf Intell Robots Syst – ident: ref16 doi: 10.1109/TR.2017.2715180 – year: 0 ident: ref1 article-title: Towards assistive feeding with a general-purpose mobile manipulator publication-title: Proc IEEE Int Conf Robot Autom -Workshop Human-Robot Interfaces Enhanced Phys Interactions – ident: ref13 doi: 10.1137/1.9781611972818.1 – ident: ref24 doi: 10.3115/v1/D14-1179 – ident: ref18 doi: 10.1016/j.robot.2014.03.003 – ident: ref7 doi: 10.1109/TASE.2014.2378150 – volume: 313 start-page: 504 year: 2006 ident: ref17 article-title: Reducing the dimensionality of data with neural networks publication-title: Science doi: 10.1126/science.1127647 – start-page: 89 year: 0 ident: ref22 article-title: Long short term memory networks for anomaly detection in time series publication-title: Eur Symp on Artif Neural Netw Computat Intell Mach Learning – ident: ref25 doi: 10.1109/IJCNN.2017.7966273 – ident: ref6 doi: 10.1145/1541880.1541882 – year: 0 ident: ref23 article-title: LSTM-based encoder-decoder for multi-sensor anomaly detection publication-title: Proc Anomaly Detection Workshop 33rd Int Conf Mach Learn – year: 2015 ident: ref32 article-title: Keras – year: 0 ident: ref4 article-title: Multimodal anomaly detection for assistive robots – ident: ref8 doi: 10.1109/IROS.2011.6095100 – ident: ref2 doi: 10.1109/MRA.2012.2229950 – ident: ref21 doi: 10.1109/DSAA.2015.7344872 – ident: ref11 doi: 10.1109/IROS.2014.6943078
SSID	ssj0001527395
Score	2.5647907
Snippet	The detection of anomalous executions is valuable for reducing potential hazards in assistive manipulation. Multimodal sensory signals can be helpful for...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1544
SubjectTerms	Anomalies Anomaly detection assistive robots Decoding deep learning in robotics and automation Detectors Failure detection and recovery Gaussian distribution Hazards Hidden Markov models Robot sensing systems Robots Sensors
Title	A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-Based Variational Autoencoder
URI	https://ieeexplore.ieee.org/document/8279425 https://www.proquest.com/docview/2299372531
Volume	3
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2377-3766 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001527395 issn: 2377-3766 databaseCode: RIE dateStart: 20160101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2377-3766 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001527395 issn: 2377-3766 databaseCode: M~E dateStart: 20160101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT-MwEB1RxAEOyy4fotCtfOCChGlqO3F8LLtUeygI8SVuUWxPJCRIViVF4sJvx3bSggRC4paDHUV5tufNeOYNwH5sGM-V4NT33KYiSXKaayNokufGmSuLDAPSE3l2lt7eqvMlOFzUwiBiSD7DI_8Y7vJtZWY-VDZImVs9LO5AR0rZ1Gq9xVO8kpiK5zeRkRpMLkY-dSs9Yl4hxScSvrM8oZXKh_M3GJXx-vc-5yf8aMkjGTVo_4IlLDdg7Z2k4CbYEQk1tQ-V9SPL6iG_fyZ_sQ7ReeIoKrmodFVTh4tH2JJxY79ISB4geUkml1en9NhZN0tunCfdRgvJaFZXXvXS4nQLrscnV3_-0baTAjVMsppKZwqHBVeYKCGk4WqIjqYJzYUjIENeIIok0sxIqU1UKMsd6Uu5FUY7ghE7P3YblsuqxB0gyHMcCvQyXlbEUaG15UWqbeo8H-Xcoy4M5n85M63MuO92cZ8FdyNSmcMl87hkLS5dOFjM-N9IbHwxdtPjsBjXQtCF3hzIrN2Djxljnnsxd8jsfj5rD1b9u5vk2x4s19MZ_oYV81TfPU770Dl9OemHRfYK4VrOlg
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB7xqAQ98ChFXZ4-cKmE2cR2Hj4ujxWIsEJ0qbhFsT2RKkFSLdlK_HtsJ7tFoqrELQdbifLZnm_GM98AHEWa8UIKTl3PbSriuKCF0oLGRaGtuTLI0COdJaNR-vAgbxfgeF4Lg4g--QxP3KO_yze1nrpQWT9ldvWwaBGWIyFY2FZr_Y2oOC0xGc3uIgPZz-4GLnkrPWFOI8WlEr6xPb6ZyrsT2JuV4frHPmgD1jr6SAYt3puwgNUX-PxGVHALzID4qtqn2riRVf1UPL6Qc2x8fJ5YkkrualU31CLjMDZk2Fow4tMHSFGR7Mf4hp5a-2bIT-tLd_FCMpg2tdO9NDj5CvfDi_HZJe16KVDNEtbQxBrDsOQSYylEorkM0RI1obiwFCTkJaKIA8V0kigdlNJwS_tSboRWlmJE1pPdhqWqrvAbEOQFhgKdkJcRUVAqZXiZKpNa30daB6kH_dlfznUnNO76XTzm3uEIZG5xyR0ueYdLD77PZ_xuRTb-M3bL4TAf10HQg70ZkHm3C59zxhz7YvaY2fn3rENYuRzfZHl2NbrehVX3njYVdw-WmskU9-GT_tP8ep4c-KX2CuRt0Kw
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=A+Multimodal+Anomaly+Detector+for+Robot-Assisted+Feeding+Using+an+LSTM-Based+Variational+Autoencoder&rft.jtitle=IEEE+robotics+and+automation+letters&rft.au=Park%2C+Daehyung&rft.au=Hoshi%2C+Yuuna&rft.au=Kemp%2C+Charles+C&rft.date=2018-07-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.eissn=2377-3766&rft.volume=3&rft.issue=3&rft.spage=1544&rft_id=info:doi/10.1109%2FLRA.2018.2801475&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2377-3766&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2377-3766&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2377-3766&client=summon