Using machine learning to developing human-like vehicle control

How do you develop a human-like autonomous driving system that would drive a 200+ mile journey across the UK, through live traffic and in natural conditions?

We ran the most complex autonomously controlled journey yet attempted in the UK, with the aim of successfully demonstrating a live traffic, end-to-end journey in a variety of settings, including country roads, A-roads and motorways.

HumanDrive was a 30-month project was part funded by the Centre for Connected and Autonomous Vehicles (CCAV) via Innovate UK and finished in 2019.


One of the most significant and innovative aspects of the project was the development of an advanced vehicle control system, designed to allow the vehicle to emulate a ‘natural’ human driving style using machine learning. Before the car was introduced to UK roads, the system was developed and subjected to a robust testing process using a range of facilities, including simulation, hardware in the loop, private test track and small sections of public roads.


The aim of HumanDrive was to:

  • Develop a vehicle capable of safe autonomous driving, in a range of conditions
  • Develop a machine learning system able to satisfactorily demonstrate ‘natural’ autonomous driving
  • Demonstrate a 200+ mile autonomous drive across the UK
  • Develop testing, validation and safety methodologies which position UK industry and academia at the forefront of autonomous vehicle knowledge and expertise
  • Develop a tailored Cyber Security Framework for the CAV sector
  • Understand the implications of CAVs on the wider transport system in terms of traffic and infrastructure.


Successful completion of this project brought the UK one step closer to having autonomous vehicles on the road, helping the UK government to fulfil its Future of Mobility Grand Challenge.

Society – Connected and Autonomous Vehicles have the potential to significantly improve safety on our roads, reduce pollution and congestion, increase accessibility for vulnerable groups, enhance our public transport, support business and the economy, release driver time for other uses, ease the pressure on a stretched transport infrastructure, and develop the transport network across the whole UK (and beyond). Furthermore, it will mimic the driving behaviour of human beings, providing an enhanced experience for the occupants and ultimately helping with acceptance of these new technologies.

Establishing UK capability in CAVs – An estimated 1m Connected and Autonomous Vehicle jobs will be created in the UK by 2035. HumanDrive is supporting this by helping to develop the necessary UK capabilities to establish a thriving CAV ecosystem.

A destination for R&D – The UK is a leader in CAV research, development and testing, backed by significant government investment, world-leading universities, and an open and innovative business environment. Learnings and technologies from this project will help to develop the autonomous vehicles and fleets of tomorrow.

Role of Connected Places Catapult

In addition to being project manager and dissemination lead for HumanDrive, we were also responsible for safety case elements as well as supporting the live trial elements of the project. This combination of a complex ‘live-traffic’ scenario and AI-controlled vehicle was ground-breaking, as such presents considerable technical and safety challenges. These challenges were met by a series of trials conducted on specialised test tracks, in simulation and open public roads to develop the AI-controlled vehicle.

CPC experts assessed and identified the myriad of hazards involved, building on the learnings from the hugely successful LUTZ Pathfinder Project. CPC Human Factors scientists also assisted in the design of trials to gather data and determine the human driving behaviour upon which much of the AV natural human driving style will be based.

The knowledge acquired was used to advise on future CAV projects and technologies, in line with CPC priorities to support UK business, increase collaboration between industry and academia, and ultimately increase economic activity in the Intelligent Mobility (IM) sector.

Further information

You can learn more about the project and find out more at