Tesla is developing an AI-based mapping system that will draw information from the company's vehicle fleet. The system will learn individual preferences and patterns across Tesla vehicles. The project could give mapping a larger role in autonomous driving.
Tesla AI Vice President Ashok Elluswamy discussed the project during the question-and-answer session of the company's third-quarter earnings call. Elluswamy said Tesla should not depend on maps supplied by outside parties. Elluswamy said Tesla is creating a new architecture for AI-based mapping and navigation. Elluswamy said information gathered collectively by Tesla vehicles would help improve maps and navigation.
The project aims to base navigation on information Tesla can collect and refresh, rather than rely entirely on an external mapping provider. That capability may matter as Tesla seeks to expand the company's driverless ride-hailing service. Navigation for that service must complement the vehicle's ability to interpret roads, reach destinations and complete the final part of a trip.
Tesla expects the system to provide functions beyond choosing routes. Elluswamy said support for trip start and end points would arrive "pretty soon" with the V15 release. Elluswamy said parking and destination-handling functions were expected over the months that follow. Elluswamy said the system would learn both personal preferences and preferences across the fleet. The earnings-call transcript does not detail the system's construction, any continued use of outside map data, or methods for comparing accuracy with established services.
Tesla's shift toward AI-based mapping and navigation faces intense safety scrutiny. Safety advocates and federal regulators warn that a camera-only approach creates critical visibility vulnerabilities. The National Highway Traffic Safety Administration intensified investigations into Tesla's Full Self-Driving software last month. The software is currently in use in Austin, Texas.
Tesla has not said the mapping project directly seeks to replace Alphabet's Google Maps as a consumer app. Autonomous vehicles may require mapping and destination-handling systems tailored to vehicle needs rather than only to people selecting routes. Execution will depend on the V15 rollout, the speed of navigation-function replacement, and demonstrated improvements in parking and destination handling under real-world conditions. Tesla's mapping system could become an important component of the company's autonomous-driving technology if those capabilities become significant to Robotaxi operations.
Tesla Developing AI-Based Mapping System for Autonomous Driving
BenzingaShare
Summary
Tesla is developing an AI-based mapping system to boost autonomous driving, as revealed in AI + crypto news. The system will use data from Tesla’s vehicle fleet to improve navigation and reduce reliance on third-party maps. Ashok Elluswamy, Tesla’s AI VP, mentioned the project during the Q3 earnings call. It supports features like parking and destination handling and could power a driverless ride-hailing service. Inflation data remains a key factor for investors tracking tech and crypto markets.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.