Behavioral Manifolds: Representing the Landscape of Grasp Affordances in Relative Pose Space

Michael Zechmair; Yannick Morel

doi:10.1109/ICRA55743.2025.11128813

Behavioral Manifolds: Representing the Landscape of Grasp Affordances in Relative Pose Space

Michael Zechmair^*
, Yannick Morel

^*Corresponding author for this work

Visual Neurosc. & Brain–Computer Interf.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

Abstract

The use of machine learning to investigate grasp affordances has received extensive attention over the past several decades. The existing literature provides a robust basis to build upon, though a number of aspects may be improved. Results commonly work in terms of grasp configuration, with little consideration for the manner in which the grasp may be (re-)produced, from a reachability and trajectory planning perspective. We propose a different perspective on grasp affordance learning, explicitly accounting for grasp synthesis; that is, the manner in which manipulator kinematics are used to allow materialization of grasps. The approach allows to explicitly map the grasp policy space in terms of generated grasp types and associated grasp quality. Results of application to a range of objects illustrate merit of the method and highlight the manner in which it may promote a greater degree of explainability for otherwise intransparent reinforcement processes.

Original language	English
Title of host publication	2025 IEEE International Conference on Robotics and Automation, ICRA 2025
Editors	Christian Ott, Henny Admoni, Sven Behnke, Stjepan Bogdan, Aude Bolopion, Youngjin Choi, Fanny Ficuciello, Nicholas Gans, Clement Gosselin, Kensuke Harada, Erdal Kayacan, H. Jin Kim, Stefan Leutenegger, Zhe Liu, Perla Maiolino, Lino Marques, Takamitsu Matsubara, Anastasia Mavromatti, Mark Minor, Jason O'Kane, Hae Won Park, Hae-Won Park, Ioannis Rekleitis, Federico Renda, Elisa Ricci, Laurel D. Riek, Lorenzo Sabattini, Shaojie Shen, Yu Sun, Pierre-Brice Wieber, Katsu Yamane, Jingjin Yu
Publisher	IEEE
Pages	5706-5712
Number of pages	7
ISBN (Electronic)	9798331541392
DOIs	https://doi.org/10.1109/ICRA55743.2025.11128813
Publication status	Published - 2 Sept 2025
Event	2025 IEEE International Conference on Robotics and Automation, ICRA 2025 - Georgia World Congress Center, Atlanta, United States Duration: 19 May 2025 → 23 May 2025 https://2025.ieee-icra.org/

Publication series

Series	Proceedings - IEEE International Conference on Robotics and Automation
ISSN	1050-4729

Conference

Conference	2025 IEEE International Conference on Robotics and Automation, ICRA 2025
Abbreviated title	ICRA 2025
Country/Territory	United States
City	Atlanta
Period	19/05/25 → 23/05/25
Internet address	https://2025.ieee-icra.org/

Access to Document

10.1109/ICRA55743.2025.11128813

Cite this

Zechmair, M., & Morel, Y. (2025). Behavioral Manifolds: Representing the Landscape of Grasp Affordances in Relative Pose Space. In C. Ott, H. Admoni, S. Behnke, S. Bogdan, A. Bolopion, Y. Choi, F. Ficuciello, N. Gans, C. Gosselin, K. Harada, E. Kayacan, H. J. Kim, S. Leutenegger, Z. Liu, P. Maiolino, L. Marques, T. Matsubara, A. Mavromatti, M. Minor, J. O'Kane, H. W. Park, H.-W. Park, I. Rekleitis, F. Renda, E. Ricci, L. D. Riek, L. Sabattini, S. Shen, Y. Sun, P.-B. Wieber, K. Yamane, ... J. Yu (Eds.), 2025 IEEE International Conference on Robotics and Automation, ICRA 2025 (pp. 5706-5712). IEEE. https://doi.org/10.1109/ICRA55743.2025.11128813

Zechmair, Michael ; Morel, Yannick. / Behavioral Manifolds : Representing the Landscape of Grasp Affordances in Relative Pose Space. 2025 IEEE International Conference on Robotics and Automation, ICRA 2025. editor / Christian Ott ; Henny Admoni ; Sven Behnke ; Stjepan Bogdan ; Aude Bolopion ; Youngjin Choi ; Fanny Ficuciello ; Nicholas Gans ; Clement Gosselin ; Kensuke Harada ; Erdal Kayacan ; H. Jin Kim ; Stefan Leutenegger ; Zhe Liu ; Perla Maiolino ; Lino Marques ; Takamitsu Matsubara ; Anastasia Mavromatti ; Mark Minor ; Jason O'Kane ; Hae Won Park ; Hae-Won Park ; Ioannis Rekleitis ; Federico Renda ; Elisa Ricci ; Laurel D. Riek ; Lorenzo Sabattini ; Shaojie Shen ; Yu Sun ; Pierre-Brice Wieber ; Katsu Yamane ; Jingjin Yu. IEEE, 2025. pp. 5706-5712 (Proceedings - IEEE International Conference on Robotics and Automation).

@inproceedings{91d9ae69fd164635b3652db6b35252b4,

title = "Behavioral Manifolds: Representing the Landscape of Grasp Affordances in Relative Pose Space",

abstract = "The use of machine learning to investigate grasp affordances has received extensive attention over the past several decades. The existing literature provides a robust basis to build upon, though a number of aspects may be improved. Results commonly work in terms of grasp configuration, with little consideration for the manner in which the grasp may be (re-)produced, from a reachability and trajectory planning perspective. We propose a different perspective on grasp affordance learning, explicitly accounting for grasp synthesis; that is, the manner in which manipulator kinematics are used to allow materialization of grasps. The approach allows to explicitly map the grasp policy space in terms of generated grasp types and associated grasp quality. Results of application to a range of objects illustrate merit of the method and highlight the manner in which it may promote a greater degree of explainability for otherwise intransparent reinforcement processes.",

author = "Michael Zechmair and Yannick Morel",

note = "Funding Information: Work partially supported by the European Union's Horizon 2020 Framework Programme for Research and Innovation under the Specific Grant Agreement No. 785907 (Human Brain Project SGA3). Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE International Conference on Robotics and Automation, ICRA 2025, ICRA 2025 ; Conference date: 19-05-2025 Through 23-05-2025",

year = "2025",

month = sep,

day = "2",

doi = "10.1109/ICRA55743.2025.11128813",

language = "English",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

publisher = "IEEE",

pages = "5706--5712",

editor = "Christian Ott and Henny Admoni and Sven Behnke and Stjepan Bogdan and Aude Bolopion and Youngjin Choi and Fanny Ficuciello and Nicholas Gans and Clement Gosselin and Kensuke Harada and Erdal Kayacan and Kim, \{H. Jin\} and Stefan Leutenegger and Zhe Liu and Perla Maiolino and Lino Marques and Takamitsu Matsubara and Anastasia Mavromatti and Mark Minor and Jason O'Kane and Park, \{Hae Won\} and Hae-Won Park and Ioannis Rekleitis and Federico Renda and Elisa Ricci and Riek, \{Laurel D.\} and Lorenzo Sabattini and Shaojie Shen and Yu Sun and Pierre-Brice Wieber and Katsu Yamane and Jingjin Yu",

booktitle = "2025 IEEE International Conference on Robotics and Automation, ICRA 2025",

address = "United States",

url = "https://2025.ieee-icra.org/",

}

Zechmair, M & Morel, Y 2025, Behavioral Manifolds: Representing the Landscape of Grasp Affordances in Relative Pose Space. in C Ott, H Admoni, S Behnke, S Bogdan, A Bolopion, Y Choi, F Ficuciello, N Gans, C Gosselin, K Harada, E Kayacan, HJ Kim, S Leutenegger, Z Liu, P Maiolino, L Marques, T Matsubara, A Mavromatti, M Minor, J O'Kane, HW Park, H-W Park, I Rekleitis, F Renda, E Ricci, LD Riek, L Sabattini, S Shen, Y Sun, P-B Wieber, K Yamane & J Yu (eds), 2025 IEEE International Conference on Robotics and Automation, ICRA 2025. IEEE, Proceedings - IEEE International Conference on Robotics and Automation, pp. 5706-5712, 2025 IEEE International Conference on Robotics and Automation, ICRA 2025, Atlanta, Georgia, United States, 19/05/25. https://doi.org/10.1109/ICRA55743.2025.11128813

Behavioral Manifolds: Representing the Landscape of Grasp Affordances in Relative Pose Space. / Zechmair, Michael; Morel, Yannick.
2025 IEEE International Conference on Robotics and Automation, ICRA 2025. ed. / Christian Ott; Henny Admoni; Sven Behnke; Stjepan Bogdan; Aude Bolopion; Youngjin Choi; Fanny Ficuciello; Nicholas Gans; Clement Gosselin; Kensuke Harada; Erdal Kayacan; H. Jin Kim; Stefan Leutenegger; Zhe Liu; Perla Maiolino; Lino Marques; Takamitsu Matsubara; Anastasia Mavromatti; Mark Minor; Jason O'Kane; Hae Won Park; Hae-Won Park; Ioannis Rekleitis; Federico Renda; Elisa Ricci; Laurel D. Riek; Lorenzo Sabattini; Shaojie Shen; Yu Sun; Pierre-Brice Wieber; Katsu Yamane; Jingjin Yu. IEEE, 2025. p. 5706-5712 (Proceedings - IEEE International Conference on Robotics and Automation).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Behavioral Manifolds

T2 - 2025 IEEE International Conference on Robotics and Automation, ICRA 2025

AU - Zechmair, Michael

AU - Morel, Yannick

N1 - Funding Information: Work partially supported by the European Union's Horizon 2020 Framework Programme for Research and Innovation under the Specific Grant Agreement No. 785907 (Human Brain Project SGA3). Publisher Copyright: © 2025 IEEE.

PY - 2025/9/2

Y1 - 2025/9/2

N2 - The use of machine learning to investigate grasp affordances has received extensive attention over the past several decades. The existing literature provides a robust basis to build upon, though a number of aspects may be improved. Results commonly work in terms of grasp configuration, with little consideration for the manner in which the grasp may be (re-)produced, from a reachability and trajectory planning perspective. We propose a different perspective on grasp affordance learning, explicitly accounting for grasp synthesis; that is, the manner in which manipulator kinematics are used to allow materialization of grasps. The approach allows to explicitly map the grasp policy space in terms of generated grasp types and associated grasp quality. Results of application to a range of objects illustrate merit of the method and highlight the manner in which it may promote a greater degree of explainability for otherwise intransparent reinforcement processes.

AB - The use of machine learning to investigate grasp affordances has received extensive attention over the past several decades. The existing literature provides a robust basis to build upon, though a number of aspects may be improved. Results commonly work in terms of grasp configuration, with little consideration for the manner in which the grasp may be (re-)produced, from a reachability and trajectory planning perspective. We propose a different perspective on grasp affordance learning, explicitly accounting for grasp synthesis; that is, the manner in which manipulator kinematics are used to allow materialization of grasps. The approach allows to explicitly map the grasp policy space in terms of generated grasp types and associated grasp quality. Results of application to a range of objects illustrate merit of the method and highlight the manner in which it may promote a greater degree of explainability for otherwise intransparent reinforcement processes.

U2 - 10.1109/ICRA55743.2025.11128813

DO - 10.1109/ICRA55743.2025.11128813

M3 - Conference article in proceeding

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 5706

EP - 5712

BT - 2025 IEEE International Conference on Robotics and Automation, ICRA 2025

A2 - Ott, Christian

A2 - Admoni, Henny

A2 - Behnke, Sven

A2 - Bogdan, Stjepan

A2 - Bolopion, Aude

A2 - Choi, Youngjin

A2 - Ficuciello, Fanny

A2 - Gans, Nicholas

A2 - Gosselin, Clement

A2 - Harada, Kensuke

A2 - Kayacan, Erdal

A2 - Kim, H. Jin

A2 - Leutenegger, Stefan

A2 - Liu, Zhe

A2 - Maiolino, Perla

A2 - Marques, Lino

A2 - Matsubara, Takamitsu

A2 - Mavromatti, Anastasia

A2 - Minor, Mark

A2 - O'Kane, Jason

A2 - Park, Hae Won

A2 - Park, Hae-Won

A2 - Rekleitis, Ioannis

A2 - Renda, Federico

A2 - Ricci, Elisa

A2 - Riek, Laurel D.

A2 - Sabattini, Lorenzo

A2 - Shen, Shaojie

A2 - Sun, Yu

A2 - Wieber, Pierre-Brice

A2 - Yamane, Katsu

A2 - Yu, Jingjin

PB - IEEE

Y2 - 19 May 2025 through 23 May 2025

ER -

Zechmair M, Morel Y. Behavioral Manifolds: Representing the Landscape of Grasp Affordances in Relative Pose Space. In Ott C, Admoni H, Behnke S, Bogdan S, Bolopion A, Choi Y, Ficuciello F, Gans N, Gosselin C, Harada K, Kayacan E, Kim HJ, Leutenegger S, Liu Z, Maiolino P, Marques L, Matsubara T, Mavromatti A, Minor M, O'Kane J, Park HW, Park HW, Rekleitis I, Renda F, Ricci E, Riek LD, Sabattini L, Shen S, Sun Y, Wieber PB, Yamane K, Yu J, editors, 2025 IEEE International Conference on Robotics and Automation, ICRA 2025. IEEE. 2025. p. 5706-5712. (Proceedings - IEEE International Conference on Robotics and Automation). doi: 10.1109/ICRA55743.2025.11128813

Behavioral Manifolds: Representing the Landscape of Grasp Affordances in Relative Pose Space

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this