TechCrunch · Mar 27, 2018
TechCrunch reports Soft Robotics’ SuperPick bin-picking system
Markdown · JSON · Original source
TechCrunch reported on March 27, 2018, that Soft Robotics had introduced SuperPick, a system for picking objects from bins with its flexible, air-filled grippers. The company said the grippers conform to different shapes and that the system can pick up objects without offline training or 3D models. Soft Robotics CEO Carl Vause told TechCrunch that SuperPick was designed to retrieve, sort and fulfill orders with little to no human intervention. The company said the system could make more than 600 picks per hour and was available at the time. TechCrunch reported that pricing depended on the job and that the company promised a cost fraction of existing systems, partly through off-the-shelf components such as webcams. The account describes warehouse picking as repetitive work that robotic systems are designed to replace. It does not establish how SuperPick performed in customers’ warehouses, what jobs it could handle reliably, or what it cost. How well could SuperPick handle varied objects and operating conditions beyond the demonstrations described?
Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.
Original source
TechCrunch · Article
Source details
Original source date: Mar 27, 2018 (2018-03-27).
Date basis: Date from the publisher’s archive: its article address or archive listing.
Added to Escape Meridian: 2026-10-29T00:24:09.269Z. First observed: 2026-10-29T00:13:56.312Z. Retrieved: 2026-10-29T00:15:37.421Z.
Referenced by
Recorded citations and public file attachments. A reference alone does not establish agreement or influence.
No public references recorded here yet.
Limits
Text as retrieved on October 29, 2026; originally published March 27, 2018. The reported pick rate and claims about training needs and cost are attributed to Soft Robotics; the account provides no independent performance or pricing data. The article does not describe customer deployments or establish how the system performed across different objects and operating conditions.
Open question
How well could SuperPick handle varied objects and operating conditions beyond the demonstrations described?
Source-stated
TechCrunch reported that Soft Robotics introduced SuperPick, a system for picking objects from bins using flexible grippers.
The startup’s latest trick is the much sought-after activity of bin picking.
Source-stated
Soft Robotics CEO Carl Vause said the system was designed to retrieve, sort and fulfill orders with little to no human intervention, without offline learning or 3D models.
It is designed to autonomously retrieve, sort and fulfill orders, with little to no human intervention
Source-stated
Soft Robotics said SuperPick could make more than 600 picks per hour.
The system is capable of more than 600 picks per hour, according to Soft Robotics.
Source-stated
TechCrunch reported that the system was available and that pricing depended on the job; the company promised it would cost a fraction of existing systems.
The system is available now. No word on pricing — that’s largely dependent on the job for which it’s being configured, but the company promises it will be available for a fraction of the cost of existing systems
Source and contributor context
TechCrunch · Publisher
The publisher is identified here. No individual author has been inferred.
Source media
Media retrieval status: unchecked.
Terms and references
Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.
Editorial provenance
Version 1. Publication ID: e68b5498-0b10-076d-123c-a6a75951e4e1.
Prepared by openai/gpt-6-luna; grounding review by anthropic/claude-opus-5.5.
Source check: passed by anthropic/claude-opus-5.5 on 2026-10-29T00:23:34.183Z. This checks fidelity to the source, not whether its claims are independently true.
Editorial selection: accept; reasons: bridge_admitted_by_model, second_opinion_categorical.
Observation: d7b83706a4b52de136fdf4b99596ff7f32b5ad660b1539308e373612ff825a70. Source text hash: 9e4a9451a62337c1184865c46a989f92125cbc0c1eb26cbe5dfa1da291928f81.
Revision and source-check history
Version 1 · 2026-10-29T00:24:09.269Z
TechCrunch reports Soft Robotics’ SuperPick bin-picking system
TechCrunch reported on March 27, 2018, that Soft Robotics had introduced SuperPick, a system for picking objects from bins with its flexible, air-filled grippers. The company said the grippers conform to different shapes and that the system can pick up objects without offline training or 3D models. Soft Robotics CEO Carl Vause told TechCrunch that SuperPick was designed to retrieve, sort and fulfill orders with little to no human intervention. The company said the system could make more than 600 picks per hour and was available at the time. TechCrunch reported that pricing depended on the job and that the company promised a cost fraction of existing systems, partly through off-the-shelf components such as webcams. The account describes warehouse picking as repetitive work that robotic systems are designed to replace. It does not establish how SuperPick performed in customers’ warehouses, what jobs it could handle reliably, or what it cost. How well could SuperPick handle varied objects and operating conditions beyond the demonstrations described?
Original source
TechCrunch · Article
Source details
Original source date: Mar 27, 2018 (2018-03-27).
Date basis: Date from the publisher’s archive: its article address or archive listing.
Added to Escape Meridian: 2026-10-29T00:24:09.269Z. First observed: 2026-10-29T00:13:56.312Z. Retrieved: 2026-10-29T00:15:37.421Z.
Limits
Text as retrieved on October 29, 2026; originally published March 27, 2018. The reported pick rate and claims about training needs and cost are attributed to Soft Robotics; the account provides no independent performance or pricing data. The article does not describe customer deployments or establish how the system performed across different objects and operating conditions.
Open question
How well could SuperPick handle varied objects and operating conditions beyond the demonstrations described?
Source-stated
TechCrunch reported that Soft Robotics introduced SuperPick, a system for picking objects from bins using flexible grippers.
The startup’s latest trick is the much sought-after activity of bin picking.
Source-stated
Soft Robotics CEO Carl Vause said the system was designed to retrieve, sort and fulfill orders with little to no human intervention, without offline learning or 3D models.
It is designed to autonomously retrieve, sort and fulfill orders, with little to no human intervention
Source-stated
Soft Robotics said SuperPick could make more than 600 picks per hour.
The system is capable of more than 600 picks per hour, according to Soft Robotics.
Source-stated
TechCrunch reported that the system was available and that pricing depended on the job; the company promised it would cost a fraction of existing systems.
The system is available now. No word on pricing — that’s largely dependent on the job for which it’s being configured, but the company promises it will be available for a fraction of the cost of existing systems
Source and contributor context
TechCrunch · Publisher
The publisher is identified here. No individual author has been inferred.
Source media
Media retrieval status: unchecked.
Terms and references
Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.
Editorial provenance
Version 1. Publication ID: e68b5498-0b10-076d-123c-a6a75951e4e1.
Prepared by openai/gpt-6-luna; grounding review by anthropic/claude-opus-5.5.
Source check: passed by anthropic/claude-opus-5.5 on 2026-10-29T00:23:34.183Z. This checks fidelity to the source, not whether its claims are independently true.
Editorial selection: accept; reasons: bridge_admitted_by_model, second_opinion_categorical.
Observation: d7b83706a4b52de136fdf4b99596ff7f32b5ad660b1539308e373612ff825a70. Source text hash: 9e4a9451a62337c1184865c46a989f92125cbc0c1eb26cbe5dfa1da291928f81.
passed · 2026-10-29T00:23:34.183Z · anthropic/claude-opus-5.5
Publication: e68b5498-0b10-076d-123c-a6a75951e4e1
attribution — pass: The reading correctly attributes the report to TechCrunch, the product to Soft Robotics, and the quoted design and training claims to CEO Carl Vause. The pick rate and cost claims are attributed to the company.
Soft Robotics CEO Carl Vause told TechCrunch
summary — pass: The title, summary and question faithfully reflect the article. A general reader can follow it: the actor is identified, bin picking is explained as picking objects from bins, and the grippers are described as flexible and air-filled. The question about performance in varied conditions follows from the evidence and is not leading.
The new SuperPick system, on the other hand, leans heavily on the company’s malleable, air-filled grippers
date — pass: The stated date of March 27, 2018 matches originalPublished at day precision and the URL path. The page was modified on 2018-03-29, but the cited claims are plainly part of the original article body. The later sidebar items (Most Popular, the event promo, the author bio) are not used. Availability and cost promises are framed as claims made at the time, with no hindsight framing. This is a publisher page, so no archive disclosure is needed.
The system is available now.
support — pass: Every claim is backed by source text: bin picking, the absence of training and 3D models, the 600+ picks per hour, availability, job-dependent pricing, the promised cost fraction via webcams, and the framing of warehouse tasks as replaceable. The stated limitations correctly note that no independent performance data exists, and the reading invents no benefits.
We don’t do the offline learning, we don’t create the 3D models, because all of the things that are driving you to create those models, we can solve with the material science.
media — pass: No media was selected, and no verified candidates were supplied, so leaving the media empty is appropriate.
Challenge or correct this reading
Send a correction or an opposing source with this reading’s URL. Disagreement and uncertainty can remain unresolved.