CLAMP: Crowdsourcing a LArge-scale in-the-wild haptic dataset with an open-source device for Multimodal robot Perception

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Thakkar, Pranav N., Sinha, Shubhangi, Baijal, Karan, Yuhan, Bian, Lackey, Leah, Dodson, Ben, Kong, Heisen, Kwon, Jueun, Li, Amber, Hu, Yifei, Rekoutis, Alexios, Silver, Tom, Bhattacharjee, Tapomayukh
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917197476003840
author Thakkar, Pranav N.
Sinha, Shubhangi
Baijal, Karan
Yuhan
Bian
Lackey, Leah
Dodson, Ben
Kong, Heisen
Kwon, Jueun
Li, Amber
Hu, Yifei
Rekoutis, Alexios
Silver, Tom
Bhattacharjee, Tapomayukh
author_facet Thakkar, Pranav N.
Sinha, Shubhangi
Baijal, Karan
Yuhan
Bian
Lackey, Leah
Dodson, Ben
Kong, Heisen
Kwon, Jueun
Li, Amber
Hu, Yifei
Rekoutis, Alexios
Silver, Tom
Bhattacharjee, Tapomayukh
contents Robust robot manipulation in unstructured environments often requires understanding object properties that extend beyond geometry, such as material or compliance-properties that can be challenging to infer using vision alone. Multimodal haptic sensing provides a promising avenue for inferring such properties, yet progress has been constrained by the lack of large, diverse, and realistic haptic datasets. In this work, we introduce the CLAMP device, a low-cost (<\$200) sensorized reacher-grabber designed to collect large-scale, in-the-wild multimodal haptic data from non-expert users in everyday settings. We deployed 16 CLAMP devices to 41 participants, resulting in the CLAMP dataset, the largest open-source multimodal haptic dataset to date, comprising 12.3 million datapoints across 5357 household objects. Using this dataset, we train a haptic encoder that can infer material and compliance object properties from multimodal haptic data. We leverage this encoder to create the CLAMP model, a visuo-haptic perception model for material recognition that generalizes to novel objects and three robot embodiments with minimal finetuning. We also demonstrate the effectiveness of our model in three real-world robot manipulation tasks: sorting recyclable and non-recyclable waste, retrieving objects from a cluttered bag, and distinguishing overripe from ripe bananas. Our results show that large-scale, in-the-wild haptic data collection can unlock new capabilities for generalizable robot manipulation. Website: https://emprise.cs.cornell.edu/clamp/
format Preprint
id arxiv_https___arxiv_org_abs_2505_21495
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLAMP: Crowdsourcing a LArge-scale in-the-wild haptic dataset with an open-source device for Multimodal robot Perception
Thakkar, Pranav N.
Sinha, Shubhangi
Baijal, Karan
Yuhan
Bian
Lackey, Leah
Dodson, Ben
Kong, Heisen
Kwon, Jueun
Li, Amber
Hu, Yifei
Rekoutis, Alexios
Silver, Tom
Bhattacharjee, Tapomayukh
Robotics
Robust robot manipulation in unstructured environments often requires understanding object properties that extend beyond geometry, such as material or compliance-properties that can be challenging to infer using vision alone. Multimodal haptic sensing provides a promising avenue for inferring such properties, yet progress has been constrained by the lack of large, diverse, and realistic haptic datasets. In this work, we introduce the CLAMP device, a low-cost (<\$200) sensorized reacher-grabber designed to collect large-scale, in-the-wild multimodal haptic data from non-expert users in everyday settings. We deployed 16 CLAMP devices to 41 participants, resulting in the CLAMP dataset, the largest open-source multimodal haptic dataset to date, comprising 12.3 million datapoints across 5357 household objects. Using this dataset, we train a haptic encoder that can infer material and compliance object properties from multimodal haptic data. We leverage this encoder to create the CLAMP model, a visuo-haptic perception model for material recognition that generalizes to novel objects and three robot embodiments with minimal finetuning. We also demonstrate the effectiveness of our model in three real-world robot manipulation tasks: sorting recyclable and non-recyclable waste, retrieving objects from a cluttered bag, and distinguishing overripe from ripe bananas. Our results show that large-scale, in-the-wild haptic data collection can unlock new capabilities for generalizable robot manipulation. Website: https://emprise.cs.cornell.edu/clamp/
title CLAMP: Crowdsourcing a LArge-scale in-the-wild haptic dataset with an open-source device for Multimodal robot Perception
topic Robotics
url https://arxiv.org/abs/2505.21495