Improving Self-Driving Car Safety And Reliability With V2X Protocols
A protocol that would help with self-driving cars is V2X or Vehicle-to-Everything. At the moment AI using machine learning techniques (deep learning) have been the focus of development for autonomous vehicle software. A communications protocol layer for self-driving cars can add further improvements for SAE Level 5 compliance. It is a protocol that supports V2V (Vehicle-to-Vehicle), V2I (Vehicle-to-Infrastructure), V2P (Vehicle-to-Pedestrian), V2H (Vehicle-to-Home), V2N (Vehicle-to-Network) and V2C (Vehicle-to-Cloud) communications. This will allow self-driving cars to communicate and share information among themselves. This will make self-driving cars aware of each other much like how people interact. Another thing this will allow is direct communication with infrastructure like intelligent buildings, smart roads, traffic lights, bridges, railroads, airports and other intelligent transportation systems.
Understanding The “Everything” in V2X
V2V Vehicle-to-Vehicle — Allows V2X enabled self-driving cars to communicate with one another.
V2I Vehicle-to-Infrastructure — Allows self-driving cars to get information from buildings, bridges, roads, traffic lights etc.
V2P Vehicle-to-Pedestrian — Makes use of pedestrian detection systems that can work with a car’s ADAS.
V2H Vehicle-to-Home — Smart homes can send and receive information directly from the car.
V2N Vehicle-to-Network — This is a mobile connection from the car to a carrier’s cellular network.
V2C Vehicle-to-Cloud — Provides direct access to cloud networks using secure TCP/IP connections.
A driverless shuttle that uses self-driving technology from NAVYA (Las Vegas, NV)
The technology uses short-range wireless signals to communicate using a network that is compliant with their standards. This can address many issues that self-driving car developers face to ensure the safety of operating driverless autonomous vehicles for commercial use, which regulators like the NHTSA require. It has always been a big concern for regulators. Having standards like this will add more to safety and reliability as well. V2X is also meant to be implemented and deployed in a decentralized way without any single authority controlling the cars. Each self-driving car will be its own independent V2X sensor system, so it doesn’t require a central system operator. The sensors built to support V2X are high-bandwidth, low-latency and support high-reliability links. These sensors are also meant to work in inclement weather, providing higher reliability when needed.
Example of how V2X can work in the real world (Source: Qualcomm)
V2X has 3 main objectives
- Road Safety
- Traffic Efficiency
- Energy Savings
Improves NLOS performance of self-driving cars (Source: Qualcomm)
Let’s discuss the 3 objectives in more detail.
Road Safety — In order to assure regulators of safety, V2X developers address main issues that improve overall safety. This includes (among others) AEB Automatic Emergency Braking, collision detection, road hazard warnings, blind spot warning and platooning or creating safe distances for autonomous vehicles on roads and highways. The deployment of AHS (Automated Highway Systems) also called “Smart Roads” provide an intelligent transportation system that aims to prevent and avoid accidents through a coordinated communications system. For example Car A will avoid bumping into Car B at all times based on a measured safety distance while on the road. Perhaps even more important is preventing self-driving cars from hitting pedestrians crossing a street. Information from the road or intersection can give a V2X enabled self-driving car a heads up on common pedestrian crossing areas and even alert them when there is an actual pedestrian crossing the street. This can work together with a self-driving car’s LiDAR or vision system.
Traffic Efficiency — Using congestion recognition and avoidance will allow self-driving cars to understand road conditions. While this is supposed to make self-driving cars more aware of traffic, it will depend a lot on the city and how well mapped the area is. The idea here is that self-driving cars can share information among themselves about the traffic conditions in their area. The use of navigation systems can interface with the self-driving car through an API. An algorithm can then be used by navigation systems to calculate routes to avoid congested roads. Other information that can be shared include the presence of roadblocks, intersection closures, accidents and other road related news. Another application of this would be intelligent route navigation in which self-driving cars can explore the best route to a destination in the shortest possible time.