StreetDrone Proposes Top 10 Safety Rules for AV Developers
Report stresses importance of retaining OE safety-related controls and systems.
OE vehicle safety systems must remain connected, in hard engineering terms and intellectually, during autonomous vehicle (AV) development, stresses Mike Potts, CEO of StreetDrone, a company specializing in AV design, engineering, and testing. “Providing the ability to allow a vehicle to drive itself means adding at least 10x in additional technology, all of which must obey safety criteria in its entirety,” Potts asserted.
To help those involved in AV R&D – from OEMs and universities to transport and delivery operators – StreetDrone has published an in-depth safety report based on its first-hand experience of ensuring that a vehicle’s own OE-installed control systems form an integral part of the overall autonomous system. The report proposes a set of “must have” rules. They address what StreetDrone considers to be “a systemic oversight across the industry of vital hardware considerations,” Potts said. “Too often, the vehicle element of the autonomous technology stack is not fully considered.”
StreetDrones claims to be the first business in Europe to have run a public-road autonomous trial using open-source, self-driving hardware in 2019. Its expertise spans the full stack of AV disciplines from hardware and mechanical design through to AI and software, together with wide experience of city center highway trials.
All vehicles used in the company’s testing and development are adapted from regular production models, with components such as steering and braking motors, sensors, cameras, a computer, data networking and 4/5G/Wi-Fi communications added. Its platform approach operates upstream, leaving the OE systems functionally intact rather than reverse-engineering or ‘hacking’ existing vehicle control system capabilities, according to Potts.
The proposed set of rules for AV design, engineering, development and testing include:
- No hacking, spoofing or reverse engineering of the base vehicle control systems (those installed by the OEM) when adding StreetDrones’ drive-by-wire system for autonomy
- No single points-of-failure in the autonomous drive-by-wire system, including in the sensors used for system monitoring
- Base vehicle safety systems, like emergency braking, always take precedence over self-driving commands
- The control “state” of the vehicle – whether the self-driving software or the safety driver is in control – must be clear and understood by the safety driver
- Comprehensive vehicle deployment protocols are based on published safety best-practices
- Clearly defined operational parameters, for instance where, geographically, any vehicles are able to travel, are published and include all aspects of safety driver responsibilities
- Safety drivers require full engineering insight and understanding across the vehicle system
- Errors must be traceable through all levels of the autonomous system’s data, including at vehicle level
- In Britain, collection and transparency of vehicle data must be compliant with the U.K. Department of Transport’s Automated Testing Code of Practice 1
- Autonomous software testing incorporates comprehensive simulation of real-world scenarios
StreetDrones’ current hardware platforms embrace the L7e class Renault Twizy and the Nissan e-NV200 in various iterations, using StreetDrone’s autonomous-ready technology conversion. Its proprietary control system works in parallel with the vehicle’s original safety systems to ensure all OEM safety validation is maintained.
University of Rochester Lab Creates New 'Reddmatter' Superconductivity Material...
INSIDERElectronics & Computers
MIT Report Finds US Lead in Advanced Computing is Almost Gone - Mobility...
Airbus Starts Testing Autonomous Landing, Taxi Assistance on A350 DragonFly...
Boeing to Develop Two New E-7 Variants for US Air Force - Mobility Engineering...
PAC-3 Missile Successfully Intercepts Cruise Missile Target - Mobility...
Air Force Pioneers the Future of Synthetic Jet Fuel - Mobility Engineering...
Driver-Monitoring: A New Era for Advancements in Sensor Technology
Manufacturing & Prototyping
Tailoring Additive Manufacturing to Your Needs: Strategies for...
How to Achieve Seamless Deployment of Level 3 Virtual ECUs for...
Electronics & Computers
Specifying Laser Modules for Optimized System Performance
The Power of Optical & Quantum Technology, Networking, &...
Electronics & Computers
Leveraging Machine Learning in CAE to Reduce Prototype Simulation and Testing
University of Rochester Lab Creates New 'Reddmatter' Superconductivity Material
INSIDERTest & Measurement
New Consortium to Develop Thermal Protection Materials for Hypersonic Vehicles
Multi-Agent RF Propagation Simulator
Low Distortion Titanium in Laser Powder Bed Fusion Systems
How to Test a Cognitive EW System