Crowdsourced mapping service addresses near-term autonomy needs

Crowdsourced mapping service addresses near-term autonomy needs

New Products |
Autonomous mapping and localization solutions provider DeepMap has announced a crowdsourced highly-scalable and economical mapping service designed to support increased autonomy for upcoming production vehicles.
By Rich Pell


The DeepMap RoadMemory mapping dervice, says the company, enables automakers to accelerate the creation and deployment of large-scale digital maps via data collected from their own fleets of passenger vehicles and trucks. It is designed to expand geographic coverage more quickly and support hands-off autonomous driving features everywhere.

“RoadMemory addresses the immediate autonomy needs of near-term production vehicles while providing a natural roadmap for future higher levels of autonomy,” says James Wu, Co-Founder and CEO of DeepMap. “DeepMap is offering a future-proof ‘best of both worlds’ approach which leverages the sensor capabilities available in cars today while increasing the fidelity of maps over time as cars become more capable.”

RoadMemory, says the company, was announced in response to demand from vehicle makers seeking large-scale, high-performance, and economical mapping capabilities to support increased autonomy for upcoming production vehicles. Improved autonomy includes driver support features such as highway assist, intelligent braking, and traffic jam pilot.

RoadMemory will automatically build maps using crowdsourced data collected from on-car sensors such as cameras, radars, and newly-available automotive-grade LiDARs. RoadMemory is sensor-agnostic, providing a high degree of flexibility to automakers who require an open system and a choice of sensors to meet their needs.

RoadMemory will work hand-in-hand with DeepMap HDR (High-Definition Reference), the company’s highest-fidelity mapping offering. RoadMemory, says the company, enables automakers to augment HDR’s market-leading fidelity and ground truth accuracy with the scalable coverage, low latency, and superior economics of crowdsourcing.

Mark Wheeler, Co-Founder and CTO of DeepMap says “Automated driver assistance and Level 2+ through Level 3 capabilities have become a critical battleground for automakers. Camera and LiDAR sensors are starting to ramp and proliferate for near-term production models. In tandem, automakers are evaluating and choosing their map source. DeepMap is providing a future-proof mapping solution for crowdsourced data that will enable more advanced functionality over time as the vehicle sensors improve and coverage expands.”

“Building maps has been a large and expensive undertaking until now,” says Wheeler. “DeepMap leverages state-of-the-art AI and mapping technologies built from the ground up for machines, by those same machines. Now it is possible to create the large-scale, fresh, accurate, open, and economical maps the transportation industry needs to advance to higher levels of autonomy.”


Linked Articles