Autonomous vehicles struggling for object recognition and decision making

Ravi Suri, Partner and Head of Infrastructure Advisory, KPMG Lower Gulf.

KPMG has been actively involved in the study of autonomous vehicles and the readiness of countries worldwide to adapt to autonomous vehicle technology. The Autonomous Vehicles Readiness Index, first issued in 2018, is a first-of-its-kind initiative which highlights global best practices to help countries accelerate their adoption of autonomous transport, capacity for adapting autonomous driving technology, as well as the progress achieved in making driverless cars a reality. 

The Index evaluates each country according to four pillars that are integral to a country’s capacity to adopt and integrate autonomous vehicles, namely: policy legislation; technology and innovation, infrastructure, and consumer acceptance.

From a technical perspective, the limitations lie in the perception and decision-making capabilities of an autonomous vehicle. Perception equates to vision and the limitation lies in the vehicle’s inability to identify surroundings accurately. This then leads to vehicles’ inability to understand how to move around unidentified objects in their way. 

Currently, the best autonomous vehicle systems incorrectly perceive the surrounding environment once every tens of thousands of hours. To overcome these challenges, there needs to be a large focus on creating redundancies in the perception system using cameras, radar, and LIDAR. Furthermore, highly detailed maps of the environment will make it easier for such cars to process their surroundings.

Human perception and their uptake of the autonomous vehicle is one of the biggest limitations facing the industry. As technological advances improve the autonomous vehicle, it may be the people’s readiness and comfort in adapting to the new norm of transportation which will present a challenge. The industry may also face legal limitations. 

One of the most critical aspects of self-driving is legislation. It may be difficult to identify who will be held liable for accidents caused by such vehicles. There is a no clear-cut definition of who the driver is, which makes it difficult to determine the party responsible for the accident and the consequences pertaining to it. 

Autonomous vehicle technology has progressed from needing driver assistance to having full autonomy. Some notable advances are the launch of the Vehicle Sensor Technology 2020 which is said to be the new cornerstone of self-driving vehicles: laser radar or LiDAR systems. 

Vehicle-to-Infrastructure communication V2I, which is the wireless exchange of data between vehicles and road infrastructure, is also disrupting the autonomous vehicle space, as is the Advanced Drive Assistance systems, which has been created to ensure the safety of the vehicle through automated functions of the driver. 

Ravi Suri, Partner and Head of Infrastructure Advisory, KPMG Lower Gulf.
Ravi Suri, Partner and Head of Infrastructure Advisory, KPMG Lower Gulf.

Key takeaways 

  • Autonomous Vehicles Readiness Index, first issued in 2018, is a first-of-its-kind initiative.
  • Autonomous Vehicles Readiness Index evaluates each country according to four pillars.
  • Limitations lie in the perception and decision-making capabilities of an autonomous vehicle. 
  • Perception equates to vision and the limitation lies in the vehicle’s inability to identify surroundings accurately. 
  • A vehicle may be unable to understand how to move around unidentified objects in their way. 
  • Advanced Drive Assistance systems have been created to ensure safety of the vehicle through automated functions of the driver.
  • The best autonomous vehicle systems incorrectly perceive the surrounding environment once every tens of thousands of hours. 
  • There needs to be a large focus on creating redundancies in the perception system using cameras, radar, and LIDAR. 
  • Highly detailed maps of the environment will make it easier for such cars to process their surroundings.
  • Human perception and their uptake of the autonomous vehicle is one of the biggest limitations facing the industry. 
  • It may be people’s readiness in adapting to the new norm of transportation which will present a challenge. 
  • One of the most critical aspects of self-driving is legislation. 
  • It may be difficult to identify who will be held liable for accidents caused by such vehicles. 
  • There is a no clear-cut definition of who is the driver, which makes it difficult to determine party responsible.