Perceiving, Understanding, and Interacting through Touch

Roberto Calandra

Stanford University - 30 September 2022

Meta AI

https://slides.com/rcalandra/stanford2022

Motivation

How to scale to more complex, unstructured domains?

Robotics

Finance

Biological Sciences

Logistics /
Decision Making

Why Robots?

Disaster Relief

Industrial Automation

Exploration

Medicine & Eldercare

State of the Art in Robotics

From YouTube: https://www.youtube.com/watch?v=g0TaYhjpOfo

What are we missing?

Key Challenges

  • Multi-modal Sensing

  • Optimized Hardware Design

  • Quick adaptation to new tasks

 

Touch Sensing

Morphological adaptation

In this talk

Model-based
Reinforcement Learning

Hardware

Software

The Importance of Touch

From the lab of Dr. Ronald Johansson, Dept. of Physiology, University of Umea, Sweden

The Importance of Touch (in Humans)

Touch Sensing is Hard

  • Interdisciplinary field which requires vertical integration. From hardware design to touch processing; From robot control to applications.
  • Many ad-hoc solutions and little re-use of existing components
    (i.e., We keep reinventing the wheel over and over)
  • High entrance bar for new researchers and practitioners
  • How can we lower the entrance bar?
  • How can we improve reproducibility?
  • How can we accelerate research by re-using existing components?

Standardization, and the creation of an ecosystem of tools

Hardware

Software

The Next Breakthrough will be in Touch

Audio

Touch

Vision

(~1890)

(~1990)

(2020s ?)

Grand Vision

+ Applications

+ Community

Hardware

Tactile Sensors in Robotics

Important factors:

  • Availability
  • Cost
  • Form factor
  • Capabilities
    (e.g., what is measured, resolution)
  • Reliability

Many many sensors in the literature:

  • Most are prototypes
  • A handful are commercially available
    or can be easily manufactured

[Wilson et al., 2019]

[Piacenza et al., 2020]

[ Fischel et al., 2012]

[Zhang et al., 2018]

[Church et al., 2019]

Vision-based Tactile Sensors

[Hillis, W. D. A High-Resolution Imaging Touch Sensor The International Journal of Robotics Research, 1982, 1, 33-44 ]

[Tanie, K.; Komoriya, K.; Kaneko, M.; Tachi, S. & Fujikawa, A. A high resollution tactile sensor Proc. of 4th Int. Conf. on Robot Vision and Sensory Controls, 1984, 251, 260]

[Begej, S. Planar and finger-shaped optical tactile sensors for robotic applications IEEE Journal on Robotics and Automation, 1988, 4, 472-484]
[Kamiyama, K.; Kajimoto, H.; Kawakami, N. & Tachi, S. Evaluation of a vision-based tactile sensor IEEE International Conference on Robotics and Automation (ICRA), 2004, 2, 1542-1547 ]

[Johnson, M. K. & Adelson, E. H. Retrographic sensing for the measurement of surface texture and shape Computer Vision and Pattern Recognition (CVPR), 2009, 1070-1077]

[Abad, A. C. & Ranasinghe, A. Visuotactile Sensors With Emphasis on GelSight Sensor: A Review IEEE Sensors Journal, 2020, 20, 7628-7638]

Credit:
[Yuan, W.; Dong, S. & Adelson, E. H. GelSight: High-Resolution Robot Tactile Sensors for Estimating Geometry and Force Sensors, Multidisciplinary Digital Publishing Institute, 2017]

DIGIT

Lambeta, M.; Chou, P.-W.; Tian, S.; Yang, B.; Maloon, B.; Most, V. R.; Stroud, D.; Santos, R.; Byagowi, A.; Kammerer, G.; Jayaraman, D. & Calandra, R.
DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation
IEEE Robotics and Automation Letters (RA-L), 2020, 5, 3838-3845

Examples of DIGIT Measurements

Lambeta, M.; Chou, P.-W.; Tian, S.; Yang, B.; Maloon, B.; Most, V. R.; Stroud, D.; Santos, R.; Byagowi, A.; Kammerer, G.; Jayaraman, D. & Calandra, R.
DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation
IEEE Robotics and Automation Letters (RA-L), 2020, 5, 3838-3845

Comparison

BioTac

DIGIT

~15,000 $

Cost

~15 $*

Resolution

29
contact points

307,200
contact points

Mounted on multi-finger hands

Open-source

https://digit.ml

1000x
Higher resolution

1000x
Cheaper

* component cost for 1000 units, not including labor

DIGIT Commercialization

  • Replicated in 20+ universities

  • Yet, it can still be challenging to manufacture a sensor without mechanical/electrical experience

  • Partnership with GelSight Inc. to commercialize DIGIT

  • >1000 sold in the first 10 months.

  • Most widespread tactile sensor in robotics!

Simulation

Touch Simulation

Simulators play a crucial role in prototyping, debugging and benchmarking new advances in robotics

  • Most rigid-body-dynamics physics engines include some form of traditional tactile sensor (i.e., low-dimensional)
  • These simulators became slower with the increasing number of contact points
  • For 1000+ contact points provided by vision-based tactile sensors, they became impractical

TACTO

Wang, S.; Lambeta, M.; Chou, P.-W. & Calandra, R.
TACTO: A Fast, Flexible and Open-source Simulator for High-Resolution Vision-based Tactile Sensors
IEEE Robotics and Automation Letters (RA-L), 2022, Online: https://arxiv.org/abs/2012.08456

Software Architecture

Wang, S.; Lambeta, M.; Chou, P.-W. & Calandra, R.
TACTO: A Fast, Flexible and Open-source Simulator for High-Resolution Vision-based Tactile Sensors
IEEE Robotics and Automation Letters (RA-L), 2022, Online: https://arxiv.org/abs/2012.08456

Rendering from Simulated DIGIT

Wang, S.; Lambeta, M.; Chou, P.-W. & Calandra, R.
TACTO: A Fast, Flexible and Open-source Simulator for High-Resolution Vision-based Tactile Sensors
IEEE Robotics and Automation Letters (RA-L), 2022, Online: https://arxiv.org/abs/2012.08456

Touch Processing

Creating a New Science of Touch Processing

Some of the open questions:

  • What are good features for touch?
  • Do we need sensor standardization?
    • What representation do we want/need for touch?
    • What sensorial information do we even want/need for touch?
  • What are the useful structures in computational models for touch?
  • What are the useful metrics to characterize touch?
  • How can we quantify the human psychophysics of touch?
  • What are the different tasks that can benefit from touch?
  • What are meaningful benchmarks for touch processing?

Very limited literature about computational processing of touch sensing

PyTouch: A Machine Learning Library
for Touch Processing

Goal: Create the equivalent of OpenCV for Touch

Lambeta, M.; Xu, H.; Xu, J.; Chou, P.-W.; Wang, S.; Darrell, T. & Calandra, R.
PyTouch: A Machine Learning Library for Touch Processing
IEEE International Conference on Robotics and Automation (ICRA), 2021, Online: https://arxiv.org/abs/2105.12791

Features of PyTouch

  • First Machine Learning library dedicated to Touch Processing
    (Based on PyTorch)
  • Hardware-agnostic abstractions for rapid experimentation
  • Native integration with DIGIT (hardware) and Tacto (simulator)
    (Working on supporting non vision-based sensors)
  • Platform for standardizing evaluation and comparison of different models
  • Touch "as-a-service"
    • Allows non-ML-experts to use SOTA ML models in their applications
    • Pre-trained models (e.g., Touch detection and slip for DIGIT)
      • (Can also be used for fast fine-tuning)
  • Open-source -- Anybody can contribute

Lambeta, M.; Xu, H.; Xu, J.; Chou, P.-W.; Wang, S.; Darrell, T. & Calandra, R.
PyTouch: A Machine Learning Library for Touch Processing
IEEE International Conference on Robotics and Automation (ICRA), 2021, Online: https://arxiv.org/abs/2105.12791

Code Example

Learning from Multiple Sensors Improve
Performance (Touch Detection Task)

Lambeta, M.; Xu, H.; Xu, J.; Chou, P.-W.; Wang, S.; Darrell, T. & Calandra, R.
PyTouch: A Machine Learning Library for Touch Processing
IEEE International Conference on Robotics and Automation (ICRA), 2021, Online: https://arxiv.org/abs/2105.12791

Benchmarks & Datasets

Benchmarks & Datasets

Benchmarks:

 

Datasets:

 
  • What are the tasks that we care about as a community?
  • Now is the time to think about Benchmarks:
    • The first enabler is accurate touch simulators (e.g., TACTO)
    • The second enabler is standardized easily available hardware (e.g., DIGIT)
  • Very few touch sensing datasets available nowadays
  • Data collection has been so far limited by the reliability of hardware
  • Simulators, and ready-available hardware will enable new and larger datasets
    (But we also need as a community to encourage and nurture this)

Learning Grasp Stability

Wang, S.; Lambeta, M.; Chou, P.-W. & Calandra, R.
TACTO: A Fast, Flexible and Open-source Simulator for High-Resolution Vision-based Tactile Sensors
IEEE Robotics and Automation Letters (RA-L), 2022, Online: https://arxiv.org/abs/2012.08456

Applications

Key Applications

Robotics

Metaverse
(AR/VR)

E-commerce

Prosthesis

Touch for the Metaverse

  • Touch is a deeply social and emotional sense
  • How can we sense, calibrate and reproduce touch?
  • How can we accurately and easily digitize objects and their physical properties into virtual worlds?

Sense

Process

Reproduce

Telepresence via Haptic Feedback

Fritsche, L.; Unverzagt, F.; Peters, J. & Calandra, R.
First-Person Tele-Operation of a Humanoid Robot
IEEE-RAS International Conference on Humanoid Robots (HUMANOIDS), 2015

Robot Learning

Some Touch Sensing Applications

Predicting Grasp Stability
[Calandra et al. 2017]

Learning how to (Re)Grasp
[Calandra et al. 2018]

Active Tactile Exploration
[Yi at al. 2016]

3D Reconstruction from Vision and Touch
[Smith et al. 2020; Smith et al. 2021]

Identify Objects from Touch

[Lin et al. 2019]

Learning to Play Piano with Touch

Xu, H.; Luo, Y.; Wang, S.; Darrell, T. & Calandra, R.
Towards Learning to Play Piano with Dexterous Hands and Touch
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) , 2022, online: https://arxiv.org/abs/2106.02040

Lambeta, M.; Chou, P.-W.; Tian, S.; Yang, B.; Maloon, B.; Most, V. R.; Stroud, D.; Santos, R.; Byagowi, A.; Kammerer, G.; Jayaraman, D. & Calandra, R.
DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation
IEEE Robotics and Automation Letters (RA-L), 2020, 5, 3838-3845

Model-based Reinforcement Learning

Lambeta, M.; Chou, P.-W.; Tian, S.; Yang, B.; Maloon, B.; Most, V. R.; Stroud, D.; Santos, R.; Byagowi, A.; Kammerer, G.; Jayaraman, D. & Calandra, R.
DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation
IEEE Robotics and Automation Letters (RA-L), 2020, 5, 3838-3845

Achieving Human-level Manipulation with Robots

To Conclude

Slack Channel

www.touch-sensing.org

Human Collaborators

Overview

  • Touch is a key sensor modality for humans and robots
  • Our goal is create an ecosystem that simplify integration and enable to perceive, understand, and interact through touch
    • Hardware
    • Simulation
    • Touch Processing
    • Benchmarks and Datasets
    • Applications
  • We want to grow and support Community
  • Towards the long-term goal of making touch sensing practical and more accessible (both in research and in the real-world)

Thank you!

DIGIT

TACTO

PyTouch

Backup Slides

Our work on touch sensing

  • Wang, S.; Lambeta, M.; Chou, L. & Calandra, R.
    TACTO: A Fast, Flexible and Open-source Simulator for High-Resolution Vision-based Tactile Sensors
    IEEE Robotics and Automation Letters (RA-L), 2022, 7, 3930-3937, Online: https://arxiv.org/abs/2012.08456

  • Smith, E. J.; Meger, D.; Pineda, L.; Calandra, R.; Malik, J.; Romero, A. & Drozdzal, M.
    Active 3D Shape Reconstruction from Vision and Touch
    Advances in Neural Information Processing Systems (NeurIPS), 2021
  • Lambeta, M.; Xu, H.; Xu, J.; Chou, P.-W.; Wang, S.; Darrell, T. & Calandra, R.
    PyTouch: A Machine Learning Library for Touch Processing
    IEEE International Conference on Robotics and Automation (ICRA), 2021
  • Smith, E. J.; Calandra, R.; Romero, A.; Gkioxari, G.; Meger, D.; Malik, J. & Drozdzal, M.
    3D Shape Reconstruction from Vision and Touch
    Advances in Neural Information Processing Systems (NeurIPS), 2020
  • Lambeta, M.; Chou, P.-W.; Tian, S.; Yang, B.; Maloon, B.; Most, V. R.; Stroud, D.; Santos, R.; Byagowi, A.; Kammerer, G.; Jayaraman, D. & Calandra, R.
    DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation
    IEEE Robotics and Automation Letters (RA-L), 2020, 5, 3838-3845
  • Padmanabha, A.; Ebert, F.; Tian, S.; Calandra, R.; Finn, C. & Levine, S.
    OmniTact: A Multi-Directional High-Resolution Touch Sensor
    IEEE International Conference on Robotics and Automation (ICRA), 2020, 618-624
  • Lin, J.; Calandra, R. & Levine, S.
    Learning to Identify Object Instances by Touch: Tactile Recognition via Multimodal Matching
    IEEE International Conference on Robotics and Automation (ICRA), 2019, 3644-3650
  • Tian, S.; Ebert, F.; Jayaraman, D.; Mudigonda, M.; Finn, C.; Calandra, R. & Levine, S.
    Manipulation by Feel: Touch-Based Control with Deep Predictive Models
    IEEE International Conference on Robotics and Automation (ICRA), 2019, 818-824
  • Calandra, R.; Owens, A.; Jayaraman, D.; Yuan, W.; Lin, J.; Malik, J.; Adelson, E. H. & Levine, S.
    More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch
    IEEE Robotics and Automation Letters (RA-L), 2018, 3, 3300-3307
  • Calandra, R.; Owens, A.; Upadhyaya, M.; Yuan, W.; Lin, J.; Adelson, E. H. & Levine, S.
    The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?
    Conference on Robot Learning (CORL), 2017, 314-323
  • Yi, Z.; Calandra, R.; Veiga, F. F.; van Hoof, H.; Hermans, T.; Zhang, Y. & Peters, J.
    Active Tactile Object Exploration with Gaussian Processes
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016, 4925-4930
  • Calandra, R.; Ivaldi, S.; Deisenroth, M. P.; Rueckert, E. & Peters, J.
    Learning Inverse Dynamics Models with Contacts
    IEEE International Conference on Robotics and Automation (ICRA), 2015, 3186-3191
  • Calandra, R.; Ivaldi, S.; Deisenroth, M. P. & Peters, J.
    Learning Torque Control in Presence of Contacts using Tactile Sensing from Robot Skin
    IEEE-RAS International Conference on Humanoid Robots (HUMANOIDS), 2015, 690-695

OmniTac

Padmanabha, A.; Ebert, F.; Tian, S.; Calandra, R.; Finn, C.; Levine, S.
OmniTact: A Multi-Directional High-Resolution Touch Sensor
IEEE International Conference on Robotics and Automation (ICRA) , 2020

Elastomer Robustness

Lambeta, M.; Chou, P.-W.; Tian, S.; Yang, B.; Maloon, B.; Most, V. R.; Stroud, D.; Santos, R.; Byagowi, A.; Kammerer, G.; Jayaraman, D. & Calandra, R.
DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation
IEEE Robotics and Automation Letters (RA-L), 2020, 5, 3838-3845

Design

Lambeta, M.; Chou, P.-W.; Tian, S.; Yang, B.; Maloon, B.; Most, V. R.; Stroud, D.; Santos, R.; Byagowi, A.; Kammerer, G.; Jayaraman, D. & Calandra, R.
DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation
IEEE Robotics and Automation Letters (RA-L), 2020, 5, 3838-3845

Replaceable Elastomer

Reflective

Reflective
+
Markers

Transparent
+
Markers

Lambeta, M.; Chou, P.-W.; Tian, S.; Yang, B.; Maloon, B.; Most, V. R.; Stroud, D.; Santos, R.; Byagowi, A.; Kammerer, G.; Jayaraman, D. & Calandra, R.
DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation
IEEE Robotics and Automation Letters (RA-L), 2020, 5, 3838-3845

Learning Grasp Stability

Calandra, R.; Owens, A.; Upadhyaya, M.; Yuan, W.; Lin, J.; Adelson, E. H. & Levine, S.
The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes?
Conference on Robot Learning (CORL), 2017, 314-323

Self-supervised Data Collection

  • Setting:
    • 7-DOF Sawyer arm
    • Weiss WSG-50 Parallel gripper
    • one GelSight on each finger
    • Two RGB-D cameras in front and on top

 

  • (Almost) fully autonomous data collection:
    • Estimates the object position using depth, and perform a random grasp of the object.
    • Labels automatically generated by looking at the presence of contacts after each attempted lift

Examples of Training Objects

Collected 6450 grasps from over 60 training objects over ~2 weeks.

Visuo-tactile Learned Model

Calandra, R.; Owens, A.; Jayaraman, D.; Yuan, W.; Lin, J.; Malik, J.; Adelson, E. H. & Levine, S.
More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch
IEEE Robotics and Automation Letters (RA-L), 2018, 3, 3300-3307

Grasp Success on Unseen Objects

83.8% grasp success on 22 unseen objects
(using only vision yields 56.6% success rate)

Gentle Grasping

  • Since our model considers forces, we can select grasps that are effective, but gentle
  • Reduces the amount of force used by 50%, with no significant loss in grasp success

Calandra, R.; Owens, A.; Jayaraman, D.; Yuan, W.; Lin, J.; Malik, J.; Adelson, E. H. & Levine, S.
More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch
IEEE Robotics and Automation Letters (RA-L), 2018, 3, 3300-3307

Traditional Sensors

Cannata, G.; Maggiali, M.; Metta, G. & Sandini, G.
An embedded artificial skin for humanoid robots
IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI), 2008, 434-438

  • Resistive or Capacitive technology
  • Several limitations:
    • Usually, measure force or orthogonal component of force
    • Relatively low density
    • Usually, low-dimensional (i.e., <100) due to cost, mechanical and communication reasons
    • Often need to be calibrated