Xing Li
Photo: SCIoI
Xing Li joined SCIoI as a PhD researcher in August 2020. His background is in robotics, machine learning, and learning from demonstration.
At SCIoI, under the supervision of Prof. Oliver Brock, he studied how robots can learn complex, contact-rich manipulation tasks from very limited human demonstrations. His work focused on helping robots generalize what they have learned to new objects and situations.
His doctoral thesis, From a Single Demonstration to a General Policy for Contact-Rich Manipulation, examines how environmental constraints can help robots build general manipulation policies from a single demonstration.
Projects
Xing Li is member of:
Doctoral Thesis
Publications +
6984777
Xing Li
1
apa
50
date
year
19933
https://www.scienceofintelligence.de/wp-content/plugins/zotpress/
%7B%22status%22%3A%22success%22%2C%22updateneeded%22%3Afalse%2C%22instance%22%3Afalse%2C%22meta%22%3A%7B%22request_last%22%3A0%2C%22request_next%22%3A0%2C%22used_cache%22%3Atrue%7D%2C%22data%22%3A%5B%7B%22key%22%3A%22ZGDAKUCQ%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Li%20and%20Brock%22%2C%22parsedDate%22%3A%222026%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BLi%2C%20X.%2C%20%26amp%3B%20Brock%2C%20O.%20%282026%29.%20%26lt%3Bi%26gt%3BFrom%20a%20Single%20Demonstration%20to%20a%20General%20Policy%20for%20Contact-Rich%20Manipulation%26lt%3B%5C%2Fi%26gt%3B%20%5BarXiv%5D.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FARXIV.2605.17601%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FARXIV.2605.17601%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22thesis%22%2C%22title%22%3A%22From%20a%20Single%20Demonstration%20to%20a%20General%20Policy%20for%20Contact-Rich%20Manipulation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xing%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Oliver%22%2C%22lastName%22%3A%22Brock%22%7D%5D%2C%22abstractNote%22%3A%22We%20present%20a%20Learning%20from%20Demonstration%20%28LfD%29%20framework%20that%20achieves%20one-shot%20generalization%20in%20multi-stage%2C%20contact-rich%20manipulation%20tasks.%20Central%20to%20our%20approach%20is%20the%20utilization%20of%20environmental%20constraints%20as%20the%20inductive%20bias.%20By%20representing%20a%20demonstration%20as%20a%20sequence%20of%20behaviors%20that%20exploit%20environmental%20constraints%2C%20the%20robot%20separates%20task-general%20structure%20--%20the%20constraint%20types%20and%20their%20transitions%20--%20from%20instance-specific%20details%20such%20as%20exact%20demonstration%20trajectories%2C%20poses%2C%20and%20local%20geometries.%20Our%20four-stage%20pipeline%20builds%20a%20complete%20policy%20on%20this%20representation%3A%20the%20robot%20first%20abstracts%20a%20single%20demonstration%20into%20environmental-constraint%20primitives%2C%20then%20disambiguates%20them%20through%20self-guided%20exploration%2C%20next%20assimilates%20targeted%20human%20corrections%20that%20handle%20out-of-distribution%20variations%2C%20and%20finally%20recovers%20the%20abstracted-away%20details%20online%20through%20compliant%20interaction.%20Because%20the%20resulting%20policy%20follows%20constraints%20rather%20than%20mimics%20trajectories%2C%20it%20generalizes%20across%20object%20poses%2C%20local%20geometries%2C%20and%20unmodeled%20contact%20dynamics.%20We%20validate%20our%20approach%20on%20seven%20real-world%20multi-stage%20contact-rich%20manipulation%20tasks%20and%20achieve%20over%2090%25%20success.%20These%20extensive%20experimental%20results%20establish%20environmental%20constraints%20as%20fundamental%20building%20blocks%20for%20efficient%20generalization%20in%20learning%20from%20demonstration.%22%2C%22thesisType%22%3A%22%22%2C%22university%22%3A%22arXiv%22%2C%22date%22%3A%222026%22%2C%22DOI%22%3A%2210.48550%5C%2FARXIV.2605.17601%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2605.17601%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-09-16T14%3A01%3A22Z%22%7D%7D%2C%7B%22key%22%3A%22ZM23QJ63%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Pfisterer%20et%20al.%22%2C%22parsedDate%22%3A%222025-05%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BPfisterer%2C%20A.%2C%20Li%2C%20X.%2C%20Mengers%2C%20V.%2C%20%26amp%3B%20Brock%2C%20O.%20%282025%29.%20A%20Helping%20%28Human%29%20Hand%20in%20Kinematic%20Structure%20Estimation.%20%26lt%3Bi%26gt%3B2025%20IEEE%20International%20Conference%20on%20Robotics%20and%20Automation%20%28ICRA%29%26lt%3B%5C%2Fi%26gt%3B%2C%2011918%26%23x2013%3B11925.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FICRA55743.2025.11127847%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FICRA55743.2025.11127847%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22A%20Helping%20%28Human%29%20Hand%20in%20Kinematic%20Structure%20Estimation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrian%22%2C%22lastName%22%3A%22Pfisterer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xing%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vito%22%2C%22lastName%22%3A%22Mengers%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Oliver%22%2C%22lastName%22%3A%22Brock%22%7D%5D%2C%22abstractNote%22%3A%22Visual%20uncertainties%20such%20as%20occlusions%2C%20lack%20of%20texture%2C%20and%20noise%20present%20significant%20challenges%20in%20obtaining%20accurate%20kinematic%20models%20for%20safe%20robotic%20manipulation.%20We%20introduce%20a%20probabilistic%20real-time%20approach%20that%20leverages%20the%20human%20hand%20as%20a%20prior%20to%20mitigate%20these%20uncertainties.%20By%20tracking%20the%20constrained%20motion%20of%20the%20human%20hand%20during%20manipulation%20and%20explicitly%20modeling%20uncertainties%20in%20visual%20observations%2C%20our%20method%20reliably%20estimates%20an%20object%26%23039%3Bs%20kinematic%20model%20online.%20We%20validate%20our%20approach%20on%20a%20novel%20dataset%20featuring%20challenging%20objects%20that%20are%20occluded%20during%20manipulation%20and%20offer%20limited%20articulations%20for%20perception.%20The%20results%20demonstrate%20that%20by%20incorporating%20an%20appropriate%20prior%20and%20explicitly%20accounting%20for%20uncertainties%2C%20our%20method%20produces%20accurate%20estimates%2C%20outperforming%20two%20recent%20baselines%20by%20195%20%25%20and%20140%20%25%2C%20respectively.%20Furthermore%2C%20we%20demonstrate%20that%20our%20approach%26%23039%3Bs%20estimates%20are%20precise%20enough%20to%20allow%20a%20robot%20to%20manipulate%20even%20small%20objects%20safely.%22%2C%22proceedingsTitle%22%3A%222025%20IEEE%20International%20Conference%20on%20Robotics%20and%20Automation%20%28ICRA%29%22%2C%22conferenceName%22%3A%222025%20IEEE%20International%20Conference%20on%20Robotics%20and%20Automation%20%28ICRA%29%22%2C%22date%22%3A%222025-05%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FICRA55743.2025.11127847%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F11127847%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A03%3A01Z%22%7D%7D%2C%7B%22key%22%3A%22NQJS577R%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Mengers%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BMengers%2C%20V.%2C%20Koenig%2C%20A.%2C%20Li%2C%20X.%2C%20Sieler%2C%20A.%2C%20Battaje%2C%20A.%2C%20%26amp%3B%20Brock%2C%20O.%20%282025%29.%20%26lt%3Bi%26gt%3BStop%20Merging%2C%20Start%20Separating%3A%20Why%20Merging%20Learning%20and%20Modeling%20Won%26%23x2019%3Bt%20Solve%20Manipulation%20but%20Separating%20the%20General%20From%20the%20Specific%20Will%26lt%3B%5C%2Fi%26gt%3B.%20International%20Conference%20on%20Robotics%20%26amp%3B%20Automation%20%28ICRA%29%20Workshop%3A%20Learning%20Meets%20Model-Based%20Methods%20for%20Contact-Rich%20Manipulation.%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Stop%20Merging%2C%20Start%20Separating%3A%20Why%20Merging%20Learning%20and%20Modeling%20Won%5Cu2019t%20Solve%20Manipulation%20but%20Separating%20the%20General%20From%20the%20Specific%20Will%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Vito%22%2C%22lastName%22%3A%22Mengers%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alexander%22%2C%22lastName%22%3A%22Koenig%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xing%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrian%22%2C%22lastName%22%3A%22Sieler%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Aravind%22%2C%22lastName%22%3A%22Battaje%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Oliver%22%2C%22lastName%22%3A%22Brock%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%22%22%2C%22conferenceName%22%3A%22International%20Conference%20on%20Robotics%20%26%20Automation%20%28ICRA%29%20Workshop%3A%20Learning%20Meets%20Model-Based%20Methods%20for%20Contact-Rich%20Manipulation%22%2C%22date%22%3A%222025%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A32%3A14Z%22%7D%7D%2C%7B%22key%22%3A%2245MJEQCX%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Li%20et%20al.%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BLi%2C%20X.%2C%20Zenkri%2C%20O.%2C%20Pfisterer%2C%20A.%2C%20%26amp%3B%20Brock%2C%20O.%20%282024%29.%20%26lt%3Bi%26gt%3BA%20Biologically%20Inspired%20Design%20Principle%20for%20Building%20Robust%20Robotic%20Systems%26lt%3B%5C%2Fi%26gt%3B.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FARXIV.2408.10192%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FARXIV.2408.10192%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22A%20Biologically%20Inspired%20Design%20Principle%20for%20Building%20Robust%20Robotic%20Systems%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xing%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Oussama%22%2C%22lastName%22%3A%22Zenkri%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Adrian%22%2C%22lastName%22%3A%22Pfisterer%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Oliver%22%2C%22lastName%22%3A%22Brock%22%7D%5D%2C%22abstractNote%22%3A%22Robustness%2C%20the%20ability%20of%20a%20system%20to%20maintain%20performance%20under%20significant%20and%20unanticipated%20environmental%20changes%2C%20is%20a%20critical%20property%20for%20robotic%20systems.%20While%20biological%20systems%20naturally%20exhibit%20robustness%2C%20there%20is%20no%20comprehensive%20understanding%20of%20how%20to%20achieve%20similar%20robustness%20in%20robotic%20systems.%20In%20this%20work%2C%20we%20draw%20inspirations%20from%20biological%20systems%20and%20propose%20a%20design%20principle%20that%20advocates%20active%20interconnections%20among%20system%20components%20to%20enhance%20robustness%20to%20environmental%20variations.%20We%20evaluate%20this%20design%20principle%20in%20a%20challenging%20long-horizon%20manipulation%20task%3A%20solving%20lockboxes.%20Our%20extensive%20simulated%20and%20real-world%20experiments%20demonstrate%20that%20we%20could%20enhance%20robustness%20against%20environmental%20changes%20by%20establishing%20active%20interconnections%20among%20system%20components%20without%20substantial%20changes%20in%20individual%20components.%20Our%20findings%20suggest%20that%20a%20systematic%20investigation%20of%20design%20principles%20in%20system%20building%20is%20necessary.%20It%20also%20advocates%20for%20interdisciplinary%20collaborations%20to%20explore%20and%20evaluate%20additional%20principles%20of%20biological%20robustness%20to%20advance%20the%20development%20of%20intelligent%20and%20adaptable%20robotic%20systems.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22%22%2C%22date%22%3A%222024%22%2C%22DOI%22%3A%2210.48550%5C%2FARXIV.2408.10192%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2408.10192%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-08-20T06%3A45%3A54Z%22%7D%7D%2C%7B%22key%22%3A%2237K8U83P%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Li%20et%20al.%22%2C%22parsedDate%22%3A%222023-10-01%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BLi%2C%20X.%2C%20Baum%2C%20M.%2C%20%26amp%3B%20Brock%2C%20O.%20%282023%29.%20Augmentation%20Enables%20One-Shot%20Generalization%20in%20Learning%20from%20Demonstration%20for%20Contact-Rich%20Manipulation.%20%26lt%3Bi%26gt%3B2023%20IEEE%5C%2FRSJ%20International%20Conference%20on%20Intelligent%20Robots%20and%20Systems%20%28IROS%29%26lt%3B%5C%2Fi%26gt%3B%2C%203656%26%23x2013%3B3663.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FIROS55552.2023.10341625%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FIROS55552.2023.10341625%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Augmentation%20Enables%20One-Shot%20Generalization%20in%20Learning%20from%20Demonstration%20for%20Contact-Rich%20Manipulation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xing%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Manuel%22%2C%22lastName%22%3A%22Baum%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Oliver%22%2C%22lastName%22%3A%22Brock%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%222023%20IEEE%5C%2FRSJ%20International%20Conference%20on%20Intelligent%20Robots%20and%20Systems%20%28IROS%29%22%2C%22conferenceName%22%3A%222023%20IEEE%5C%2FRSJ%20International%20Conference%20on%20Intelligent%20Robots%20and%20Systems%20%28IROS%29%22%2C%22date%22%3A%222023-10-1%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FIROS55552.2023.10341625%22%2C%22ISBN%22%3A%22978-1-6654-9190-7%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F10341625%5C%2F%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-08-20T06%3A33%3A51Z%22%7D%7D%2C%7B%22key%22%3A%22J4G585A3%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Li%20and%20Brock%22%2C%22parsedDate%22%3A%222022%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BLi%2C%20X.%2C%20%26amp%3B%20Brock%2C%20O.%20%282022%29.%20Learning%20From%20Demonstration%20Based%20on%20Environmental%20Constraints.%20%26lt%3Bi%26gt%3BIEEE%20Robotics%20and%20Automation%20Letters%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B7%26lt%3B%5C%2Fi%26gt%3B%284%29%2C%2010938%26%23x2013%3B10945.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FLRA.2022.3196096%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FLRA.2022.3196096%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Learning%20From%20Demonstration%20Based%20on%20Environmental%20Constraints%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xing%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Oliver%22%2C%22lastName%22%3A%22Brock%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%2210%5C%2F2022%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FLRA.2022.3196096%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F9849096%5C%2F%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%222377-3766%2C%202377-3774%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-08-20T06%3A57%3A51Z%22%7D%7D%5D%7D
Li, X., & Brock, O. (2026). From a Single Demonstration to a General Policy for Contact-Rich Manipulation [arXiv]. https://doi.org/10.48550/ARXIV.2605.17601
Pfisterer, A., Li, X., Mengers, V., & Brock, O. (2025). A Helping (Human) Hand in Kinematic Structure Estimation. 2025 IEEE International Conference on Robotics and Automation (ICRA), 11918–11925. https://doi.org/10.1109/ICRA55743.2025.11127847
Mengers, V., Koenig, A., Li, X., Sieler, A., Battaje, A., & Brock, O. (2025). Stop Merging, Start Separating: Why Merging Learning and Modeling Won’t Solve Manipulation but Separating the General From the Specific Will. International Conference on Robotics & Automation (ICRA) Workshop: Learning Meets Model-Based Methods for Contact-Rich Manipulation.
Li, X., Zenkri, O., Pfisterer, A., & Brock, O. (2024). A Biologically Inspired Design Principle for Building Robust Robotic Systems. arXiv. https://doi.org/10.48550/ARXIV.2408.10192
Li, X., Baum, M., & Brock, O. (2023). Augmentation Enables One-Shot Generalization in Learning from Demonstration for Contact-Rich Manipulation. 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 3656–3663. https://doi.org/10.1109/IROS55552.2023.10341625
Li, X., & Brock, O. (2022). Learning From Demonstration Based on Environmental Constraints. IEEE Robotics and Automation Letters, 7(4), 10938–10945. https://doi.org/10.1109/LRA.2022.3196096
For the Public -
Science of Intelligence Fair 2023
