JohnDe
La dolce vita
- Joined
- 11 March 2020
- Posts
- 4,984
- Reactions
- 7,455
Tesla .... now working with Lidar (after a change of heart by Musk) so probably understand the problems.
Would have liked the Waymo Level 4 system in the test. They have much more real life experience and would have shat it in I believe.
Unless I have missed some recent news, Tesla only use LiDAR as a calibration tool to help its AI learn depth perception.
LiDAR stands for Light Detecting and Ranging – essentially using lasers to measure distances. A laser pulse is sent out, and the time it takes to return is measured – providing extremely accurate distance measurements.
Tesla uses it exactly how it's described – they use it to gather ground-truth data. This data is then used to feed Tesla’s Full Self Driving system – which helps validate its vision-only system's accuracy. LiDAR provides very accurate measurements to help ensure that FSD’s perception of space is accurate – and is only used by Tesla to ensure that its AI technology which is the brains of FSD is capable of accurately interpreting depth from just visual data.
While Tesla doesn't use LiDAR in their production vehicles for self-driving, they do use it for gathering ground truth data to validate their vision-based system. This means they use LiDAR sensors to create highly accurate 3D maps of the environment, which are then used to train and refine their AI models that rely on cameras for perception.
Here's a more detailed explanation:
- Ground Truth Validation:
Tesla uses LiDAR to obtain precise measurements of distance and depth, which serve as a benchmark to assess the accuracy of their camera-based system.
- Refining AI Models:
By comparing the LiDAR data with the camera's perception, Tesla can identify areas where the camera system needs improvement and refine its AI algorithms accordingly.
- Vision-Only Approach:
Tesla's long-term goal is to develop a fully autonomous driving system that relies solely on cameras and other sensors, without needing LiDAR for regular operation.
- Scalability:
Tesla's reliance on cameras is driven by the desire for a scalable solution, meaning their self-driving technology can adapt to new environments without requiring extensive pre-mapping of every location.
- Cost and Aesthetics:
Elon Musk has previously stated that LiDAR is a "crutch" and that relying on it for self-driving is a "fool's errand" due to cost, complexity, and aesthetic concerns.
- Tesla's Use of Luminar Sensors:
Tesla has purchased LiDAR sensors from Luminar for ground truth validation, demonstrating their commitment to refining their vision-based system.

Tesla Vehicles Spotted With LiDAR: What Do They Use It For?
Tesla uses LIDAR for ground-truth validation and testing of FSD's depth perception and distance measuring.
