A camera that can see through walls
Bill Abster from Applied Electromagnetics discusses his company's breakthrough technology that uses radio waves and high-frequency antennas to create 3D images of objects behind opaque materials. The system processes echoes in real-time using GPUs to generate detailed depth maps, and the company has achieved significant progress in just 4 months by maintaining rapid iteration cycles.
Summary
Bill Abster, founder of Applied Electromagnetics, explains how his company is developing cameras that can see through opaque materials like drywall and marble. The idea originated from a personal experience during home remodeling when hidden structural problems behind walls caused expensive repairs, prompting Abster to develop a solution leveraging his background in radars and antennas.
The technology operates using radio waves at high frequencies, requiring operation of many antennas simultaneously. The system captures complete 3D images with depth information by processing echoes in real-time. Abster demonstrates the capability using concrete examples: stickers placed behind drywall on acrylic, and construction elements (studs, junction boxes, pipes, cables) behind marble slabs. The resulting images are accurate to pixel-level measurements that match physical world dimensions.
The technology became feasible through two key developments: the widespread availability of high-frequency chipsets (multichips) and the GPU revolution, which enables processing of the large data streams generated by the echoes to be done on-the-go and converted into images. Abster notes the company has been operating full-time for only 4 months while building 'day and night,' with the demonstrated device being version three. He emphasizes that rapid iteration speed is critical for hardware companies, continuously releasing iterations to identify bottlenecks and opportunities for parallel development.
Key Insights
- The through-wall imaging technology became feasible because high-frequency antenna chipsets became widely available and GPU computing enabled real-time processing of the large echo data streams to generate images
- The system captures complete 3D images with precise depth information that maintains one-to-one correspondence with actual physical world dimensions when measured by pixels
- The company was founded based on a personal problem: discovering expensive hidden structural issues behind walls during home remodeling that motivated building a solution
- Despite being only 4 months into full-time operation, the company has already developed three iterations of their device by maintaining constant building and iteration cycles
- For hardware companies, maintaining rapid iteration speed is more important than waiting to perfect a design; the key is continuously releasing versions while identifying bottlenecks and parallel development opportunities
Topics
Transcript
[0:00] Uh my name is Bill Abster. We're building applied electronamics doing new kind of cameras that can see through an opaque material. >> How did you get into that idea? >> Uh it actually started from a personal experience. During our remodels, we discovered a bunch of stuff that existed behind the walls that cost us a lot of money to fix. So we decided that there needs to be something that can see through the walls. My background is in radars and antennas. And I figured out we can do it with radio waves and we've been building it ever since. If you want to do it right, then you have to operate a lot of antennas at…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Y Combinator
What If We Stopped Using GPUs? | YC Paper Club
A YC Paper Club discussion exploring alternatives to GPU-based computing, featuring presentations on optical computing, neuromorphic chips, and biological computing approaches. Speakers argue that GPU efficiency (FLOPS per joule) has plateaued, necessitating fundamentally different computational substrates inspired by the brain's 20-watt energy efficiency.
Robotic factories that build robots
Tensor is building a 12,000 sq ft robotic factory that manufactures robots, including humanoids and specialized grippers. The company, founded by Berkeley researchers with autonomous vehicle and manufacturing backgrounds, treats the entire factory as a learning system that improves manufacturing processes with each customer order.
New LLMs Are Unlocking Robot-Use Agents
This discussion explores how large language models like Claude (Astra) are enabling robot control through code generation and tool use, building on foundational work like RT2 and visual language-action models. The speakers from Waddle Labs and RoboCurve explain how models trained on diverse data modalities—including web text, computer usage, and coding—are converging toward general-purpose robot agents that can perform complex physical tasks within the next 2 years.
Rocket cargo delivery anywhere on Earth in minutes
Matthew, CEO of Hover Arrow, discusses the company's mission to deliver cargo anywhere on Earth within minutes using rocket technology. The startup has secured $1.37 billion in commercial letters of intent, with primary focus on military applications and emerging interest from industries requiring rapid, temperature-controlled delivery of perishable goods.
Autonomous construction on Earth and beyond
James, co-founder of Fossma Robotics, discusses building autonomous construction equipment for large-scale infrastructure on Earth with the long-term goal of enabling construction on Mars and the moon. The company has already deployed systems that installed 11,000 solar panels and recently signed a major contract with the top construction company in the US.