DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation
About
Despite decades of research, general purpose in-hand manipulation remains one of the unsolved challenges of robotics. One of the contributing factors that limit current robotic manipulation systems is the difficulty of precisely sensing contact forces -- sensing and reasoning about contact forces are crucial to accurately control interactions with the environment. As a step towards enabling better robotic manipulation, we introduce DIGIT, an inexpensive, compact, and high-resolution tactile sensor geared towards in-hand manipulation. DIGIT improves upon past vision-based tactile sensors by miniaturizing the form factor to be mountable on multi-fingered hands, and by providing several design improvements that result in an easier, more repeatable manufacturing process, and enhanced reliability. We demonstrate the capabilities of the DIGIT sensor by training deep neural network model-based controllers to manipulate glass marbles in-hand with a multi-finger robotic hand. To provide the robotic community access to reliable and low-cost tactile sensors, we open-source the DIGIT design at https://digit.ml/.
Key insights
What tactile sensing problem does DIGIT address?
Robotic in-hand manipulation needs precise contact-force sensing, but existing vision-based tactile sensors are bulky, wear quickly, and are hard to manufacture. DIGIT is a compact, low-cost vision-based sensor using a camera, LEDs, and a deformable elastomer to capture sub-millimeter surface detail, mountable on multi-finger hands.
How does DIGIT differ from prior vision-based sensors?
DIGIT is smaller (20x27x18 mm vs. 35x60x35 mm for GelSight) and costs about 15 USD per sensor at 1000-unit batches. Its elastomer showed 0.3% degradation after 5 abrasion passes versus 482% for a prior gel, which became unusable after testing.
What practical use does DIGIT demonstrate?
The researchers demonstrate rolling glass marbles between two fingers of an Allegro robot hand, using tactile images to guide model predictive control. The open hardware design supports reproducible robotics experiments; the paper does not establish commercial deployment.
What limitations do the authors acknowledge?
About 25% of marble manipulation trials ended in drops, attributed to planning inaccuracies and actuation noise. The authors suggest improving low-level control and collecting more data. Future work includes further miniaturization and designing curved, omni-directional sensing fields.