# How Autonomous Vehicles Use Different Camera Lenses for Better Vision

> This patent describes a specific arrangement of cameras for self-driving vehicles, using multiple forward-facing cameras with different focal lengths and a pair of backward-facing cameras with identical focal lengths to achieve comprehensive vision.

- **Patent:** US 12231783
- **Original title:** Sensor layout for autonomous vehicles
- **Owner:** Tusimple
- **Granted:** 2025
- **Status:** Active
- **Times cited:** 0
- **Field:** automotive, software, consumer_electronics, telecommunications, ai_ml

## What it does

This system provides an autonomous vehicle with an optimized camera setup for seeing its surroundings. It includes several cameras facing forward, each designed with a different focal length to capture objects at various distances, like a 6 mm lens for wide views, a 12 mm lens for mid-range, and a 25 mm lens for far-off objects (Claim 3). The vehicle also has two cameras facing backward, both sharing the same focal length (Claim 1). One of the forward-facing cameras is designed to have the same focal length as these backward cameras. Optionally, the system can also include cameras on the left and right sides of the vehicle (Claim 7), along with LiDAR and RADAR sensors to measure distances and detect objects (Claims 8-9). This combination aims to provide a full 360-degree view around the vehicle (Claim 6).

## What it does NOT cover

- Does not cover autonomous vehicle camera systems that use only one forward-facing camera.
- Does not cover systems where all forward-facing cameras have the exact same focal length.
- Does not cover systems where the two backward-facing cameras have different focal lengths.
- Does not require the inclusion of LiDAR or RADAR sensors, as these are listed as optional additions in the claims.
- Does not cover systems where none of the forward-facing cameras share a focal length with the backward-facing cameras, as Claim 1 specifies one forward camera must match.

## The clever bit

The novelty lies in precisely combining multiple forward-facing cameras with varied focal lengths for detailed, multi-range vision, while simultaneously employing two backward-facing cameras with identical focal lengths, and ensuring one forward camera matches the backward cameras' focal length. This specific arrangement aims to balance wide-angle coverage with long-range detail, both front and back.

## Real-world examples

1. Autonomous semi-trucks
2. Self-driving delivery vehicles
3. Robo-taxis
4. Advanced driver-assistance systems (ADAS) in passenger cars

## Why it matters

The ability of an autonomous vehicle to perceive its environment accurately is crucial for safety and functionality. This patent focuses on a specific camera configuration to enhance perception, allowing the vehicle to detect objects across a wide range of distances and directions. Such optimized sensor layouts are fundamental to the development and deployment of reliable self-driving technology, impacting how autonomous trucks and cars navigate complex environments.

## Frequently asked questions

### What does How Autonomous Vehicles Use Different Camera Lenses for Better Vision cover?

This patent describes a specific arrangement of cameras for self-driving vehicles, using multiple forward-facing cameras with different focal lengths and a pair of backward-facing cameras with identical focal lengths to achieve comprehensive vision.

### Who owns patent US 12231783?

Tusimple owns this patent, granted in 2025.

### When does this patent expire?

This patent is expected to expire on August 3, 2043, when the invention enters the public domain.

### What problem does this patent solve?

The ability of an autonomous vehicle to perceive its environment accurately is crucial for safety and functionality. This patent focuses on a specific camera configuration to enhance perception, allowing the vehicle to detect objects across a wide range of distances and directions. Such optimized sensor layouts are fundamental to the development and deployment of reliable self-driving technology, impacting how autonomous trucks and cars navigate complex environments.

### What does this patent NOT cover?

Does not cover autonomous vehicle camera systems that use only one forward-facing camera.

**Full plain-English explainer:** https://patentbrief.org/patent/us/12231783/sensor-layout-for-autonomous-vehicles

**Original patent:** https://patents.google.com/patent/US12231783

---

_Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._


## Related patents

Semantically similar inventions in the PatentBrief corpus:

- [How to Combine Wide-Angle LiDAR Depth with Standard Camera Images](https://patentbrief.org/patent/us/11543533/systems-and-methods-for-wide-angle-lidar-using-non-uniform-magnification-optics) — This patent describes a method for combining a wide-angle depth map from a LiDAR sensor, which has unevenly spaced pixels, with a standard camera image by first correcting the depth map's pixel distribution and then merging the two for a complete view.
- [How Car Safety Systems Turn Off When Sensors Disagree](https://patentbrief.org/patent/us/11702088/vehicular-driving-assist-system-with-sensor-offset-correction) — This patent describes a car safety system that uses both a camera and a radar sensor to detect objects, and if their detections don't match up, it can disable parts of the driving assistance for safety.
- [How Autonomous Cars Process Sensor Data for Driving](https://patentbrief.org/patent/us/20220161815/autonomous-vehicle-system) — Intel's 2020 patent describes a system for autonomous vehicles that cleans and standardizes data from various sensors before using it to perceive the environment and make driving decisions.
- [How Self-Driving Cars Find Clear Paths Between Objects](https://patentbrief.org/patent/us/10733420/systems-and-methods-for-free-space-inference-to-break-apart-clustered-objects-in) — This patent describes a method for vehicles, especially self-driving ones, to use lidar data and a 3D grid to precisely identify open spaces between obstacles, helping them navigate safely.
- [Drone Navigation Using Cameras and Echolocation](https://patentbrief.org/patent/us/9562773/autonomous-vehicle-navigation-system-and-method) — This 2017 patent describes a drone navigation system that uses both cameras and echolocation sensors to detect obstacles and find its way, with echolocation taking priority for immediate threats.
