HD Mapless Autonomous Driving Technology

by Eran Ofir, CEO | Imagry

As an AI, hardware-agnostic autonomous driving software company, our primary goal is to create the software necessary to autonomously drive passenger cars and buses on public roads.

Perception and Motion Planning for AI Autonomous Driving

Imagry has developed a software stack that uses regular camera feeds to perceive the immediate environment around the self-driving vehicle in real-time. Several deep neural networks process the video feeds from the cameras, resulting in a perception map that is fed to Imagry’s second software stack, which handles the motion planning phase. Unlike rule-based approaches, Imagry leverages a neural network approach to motion planning. By imitating human behavior, Imagry teaches its network to drive, producing a path solution to traverse the nearby area covered by the perception map.

Although we are a software company, we built the necessary hardware to showcase our software stack on the road. We integrated our test autonomous driving system into a passenger vehicle and took it for a drive in downtown Haifa, Israel, an area that’s notoriously challenging to navigate. Over the past four years, in addition to Haifa, we have driven, safely and without any accidents, in San Jose, California; Tempe, Arizona; Frankfurt, Germany; and Tokyo, Japan. We were recently offered a unique opportunity to showcase our capabilities in an Israel government-funded projects to deploy autonomous buses on public roads.

Our approach of teaching the AI to self-drive in general and not only in a specific location allows our software stack to drive ‘out-of-the-box’ in new locations the vehicle has never visited. It behaves just like a human driver who can get off a plane in a new country, rent a car, and drive.

Motion Planning & Neural Networks Functions

Humans underestimate the amount of computing our brains do to perceive the environment and then traverse it in order to drive. Perception involves understanding the car’s immediate surroundings, including the road’s location, lanes, crosswalks, and other markings. It requires identifying traffic lights and their signal colors, reading signs along the road, recognizing the position of other cars and pedestrians, and predicting their movements. Much like for humans, this perception data is achieved solely through visual sensors, specifically cameras.

Also known as path planning, motion planning is an algorithm that produces a path to traverse the immediate surroundings while considering things like the position, motion (including velocity and acceleration), and trajectory of other vehicles and pedestrians. In an intersection, for example, our motion planning software creates a path to go straight, turn right, or turn left. It ensures, for example, the autonomous vehicle maintains a safe distance when driving alongside parked cars and through other road obstacles, such as construction sites. In contrast to traditional autonomous driving software, Imagry’s approach does not involve encoding rules; rather, we teach a neural network to perform the task.

The problem we face in autonomous driving is that the world is diverse, and writing specific rules to cope with every possible option is impractical. The wonderful thing about neural networks is their ability to adapt to situations they have not seen and hence have not practiced navigating. The adaptation is done by producing an AI-based solution based on a combination of solutions that the neural network already learned, just like humans do.

Simplicity & Versatility for Self-Driving Best Practices

This ability to adapt, or generalization capability, is crucial to developing autonomous vehicles. By applying neural networks to solve every task involved in driving, we ensure that autonomous vehicles can adapt to new situations and not break down when faced with a situation that involves something a little different than what was learned previously. This ability to generalize is one of the benefits Imagry provides to the autonomous industry.

Imagry avoids creating a “big black box” situation by breaking down the larger tasks of perception and motion planning into smaller ones, each governed by a specific neural network. When something does not work properly, we can dive in and pinpoint the specific faulty neural network and then strengthen it. The alternative, a complex neural network that handles multiple tasks can become a big black box, makes it difficult to identify the source of any issues that may arise.

Successful Autonomous Vehicle Pilot Programs

Imagry has two pilot programs in progress that may interest developers of autonomous cars. The first is a shuttle bus that commenced operation in February 2023 in the Sheba medical center in Israel, the biggest medical center in the Middle East. The medical center campus is about 800 dunam (200 acres), about the size of a small village, and is visited daily by more than 50,000 people using all modes of transportation: private cars, taxis, scooters, public buses, etc.

The second program provides an autonomous bus that can drive on a public road. This bus will be integrated into an existing bus line in the city of Nahariya, Israel. The idea is to use our AI-based autonomous driving technology to solve the bus driver shortage problem, a common problem that Israel shares with the world.

Next stop, full autonomy!

Are you coming? Got a question for us?

    Company Locations

    Imagry, Inc.
    1630 Old Oakland Rd.
    Suite #A112
    San Jose CA 95131
    USA
    Imagry (Israel) Ltd.
    53 Derekh HaAtsma'ut
    3rd Floor
    Haifa 3303327
    Israel

    Accessibility Toolbar