Robohub.org
 

Headlights that see through rain; A robotic seamstress


by
20 July 2012



share this:
Normally I don’t write about scientific breakthroughs that may or may not turn into commercial products. But these two are sure winners and I wanted to share them with you.

Headlights That See Through Rain

Graphic courtesy of Carnegie Mellon Illumination and Imaging Lab.

A while back the Navy, NSF, Samsung and Intel collaborated in a research project to improve visibility in poor weather conditions. Tools were developed for removing fog, haze, mist, rain, snow, dust and murky waters from images and videos. But, and this was the original motivation for this project, they wanted helmsmen and drivers to see better with their own eyes in those very same poor weather conditions.

Hence the development at Carnegie Mellon University’s Robotics Institute of a smart headlight system. Last week CMU released papers and videos showing that their smart headlight system can improve visibility by constantly redirecting light to shine between particles of precipitation.

“If you’re driving in a thunderstorm, the smart headlights will make it seem like it’s a drizzle,” said Srinivasa Narasimhan, associate professor of robotics.

The system uses a camera to track the motion of raindrops and snowflakes and then applies a computer algorithm to predict where those particles will be just a few milliseconds later. The light projection system then adjusts to deactivate light beams that would otherwise illuminate the particles in their predicted positions.

“A human eye will not be able to see that flicker of the headlights,” Narasimhan said. “And because the precipitation particles aren’t being illuminated, the driver won’t see the rain or snow either.”

To people, rain can appear as elongated streaks that seem to fill the air. To high-speed cameras, however, rain consists of sparsely spaced, discrete drops. That leaves plenty of space between the drops where light can be effectively distributed if the system can respond rapidly, Narasimhan said.

The CMU team is now engineering a more compact version which will be able to be installed in a car for road testing.

Amazing! I can’t wait to get it installed on my new car.

***

A Factory To Make Uniforms

Recently there was a lot of news uproar over the fact that China was producing the uniforms and flags for the American Olympic team. The Pentagon is worried about the same situation regarding our country’s military uniforms. Every year, the Pentagon spends $4 billion on uniforms. In an effort to cut costs, increase efficiency, and keep production in America, DARPA has awarded a $1.25 million contract to SoftWear Automation, Inc. – a corporation started by a retired GA Tech professor who wrote a paper on the subject two years ago. The project is to develop “complete production facilities that produce garments with zero direct labor” – in other words, a robot factory that can make uniforms from beginning to end without human operators.

Research version of a robotic sewing machine with high-speed vision and servo-controller. Photo: SoftWear Automation.

SoftWear Automation’s solution is a fully automated work cell which will automatically make a sewn item, e.g., a pair of pants, shorts, a work shirt, etc. This involves controlling the cutting and sewing machines based on machine vision and moving coil servo motors (two are shown in magenta in the work cell image shown below). The sewing machines will have servo controlled rotations so that sewing can be dynamically changed in direction without fabric rotation.

Rendering of automated sewing work cell. Image: SoftWear Automation.

This is not an inexpensive undertaking. Like many industrial robotic solutions, there is serious up-front capital expenditure. But like most robot applications, payback is swift in steady product quality and output. Also like most industrial robotic applications, costs are dropping quickly as sensors, software and CPUs become more capable and available at very low cost.

The DoD, with this contract, may be leading the way to retrieving from offshore a good portion of the sewn items business that are presently produced in China, Vietnam and other low-labor-cost areas.



tags: ,


Frank Tobe is the owner and publisher of The Robot Report, and is also a panel member for Robohub's Robotics by Invitation series.
Frank Tobe is the owner and publisher of The Robot Report, and is also a panel member for Robohub's Robotics by Invitation series.





Related posts :



Teaching robots to map large environments

  05 Nov 2025
A new approach could help a search-and-rescue robot navigate an unpredictable environment by rapidly generating an accurate map of its surroundings.

Robot Talk Episode 131 – Empowering game-changing robotics research, with Edith-Clare Hall

  31 Oct 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Edith-Clare Hall from the Advanced Research and Invention Agency about accelerating scientific and technological breakthroughs.

A flexible lens controlled by light-activated artificial muscles promises to let soft machines see

  30 Oct 2025
Researchers have designed an adaptive lens made of soft, light-responsive, tissue-like materials.

Social media round-up from #IROS2025

  27 Oct 2025
Take a look at what participants got up to at the IEEE/RSJ International Conference on Intelligent Robots and Systems.

Using generative AI to diversify virtual training grounds for robots

  24 Oct 2025
New tool from MIT CSAIL creates realistic virtual kitchens and living rooms where simulated robots can interact with models of real-world objects, scaling up training data for robot foundation models.

Robot Talk Episode 130 – Robots learning from humans, with Chad Jenkins

  24 Oct 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Chad Jenkins from University of Michigan about how robots can learn from people and assist us in our daily lives.

Robot Talk at the Smart City Robotics Competition

  22 Oct 2025
In a special bonus episode of the podcast, Claire chatted to competitors, exhibitors, and attendees at the Smart City Robotics Competition in Milton Keynes.

Robot Talk Episode 129 – Automating museum experiments, with Yuen Ting Chan

  17 Oct 2025
In the latest episode of the Robot Talk podcast, Claire chatted to Yuen Ting Chan from Natural History Museum about using robots to automate molecular biology experiments.



 

Robohub is supported by:




Would you like to learn how to tell impactful stories about your robot or AI system?


scicomm
training the next generation of science communicators in robotics & AI


 












©2025.05 - Association for the Understanding of Artificial Intelligence