listen to this article ![]() |
![Screenshot of Tangram Vision’s new LiDAR sensor comparison tool](https://www.therobotreport.com/wp-content/uploads/2024/05/lidar-comparison-tool-tangram-vision.jpg)
Screenshot of Tangram Vision’s LiDAR comparison tool
LiDAR (Light Detection and Ranging) is a detection method that uses light in the form of a pulsed laser to measure distance. LiDAR is useful for autonomy in several key functions such as obstacle avoidance, object detection, and object identification. 3D data from rotating LiDAR is often a key input for navigation systems for autonomous vehicles and robots.
If you're looking for a LiDAR sensor to add to your robot, Tangram Vision wants to make the evaluation process simpler. Tangram Vision, a startup building software and hardware for robotic perception, has launched an interactive tool called “Spinning LiDAR Visualizer” that allows you to compare spinning LiDAR models.
Users can compare 28 LiDAR models from leading manufacturers such as Hesai, Ouster, Quanergy, RoboSense, and Velodyne. The visualizer allows you to select one or two LiDAR sensors to analyze and compare their maximum range, 10% reflectance range, angular resolution and field of view. You can click and drag for different perspectives, insert tools elsewhere, or even modify them in GitLab.
“From the beginning, our goal at Tangram Vision has been to build the tools and resources we’ve always wanted to have as perception engineers,” said Adam Rodnitzky, COO and co-founder of Tangram Vision. “Some of it comes in the form of products, like calibration tools, and some of it comes in the form of open source projects, like this new LiDAR visualization and comparison tool.”
In 2021, Tangram Vision launched an interactive depth sensor visualizer. Rodnitzky said user response has been positive, with many requesting similar tools for LiDAR sensors. Rodnitzky said the team has compiled specifications for dozens of solid-state directional LiDARs to be added to existing or new visualizers in the future.
“Generally speaking, there is still a lack of good resources for perception engineers. For many tasks, a lot of time is spent on research, trial and error, or building new pathways that haven’t been created yet,” Rodnitzky said. “We are committed to building a bank of resources so our engineers can focus more on productive work rather than the repetitive tasks they already have to solve.”
Tangram Vision recently released its 2024 Cognitive Industry Market Map, which provides a look at more than 100 companies developing hardware and software for robots, autonomous vehicles, and more.
In late 2023, Tangram Vision announced its first foray into perception hardware with its HiFi 3D depth sensor. HiFi combines a pair of 136° DFOV 2.2MP global shutter IR stereo with a 136° DFOV 2MP RGB camera and dual active projectors to provide high-quality depth maps. The company said the onboard deep learning matrix multiplication accelerator operates at 8 TOPS and is coupled with 16Gb onboard memory. This allows developers to run machine learning training and processes at the edge and train models using continuously calibrated, high-accuracy depth data.