Understand this story
In an interview, Empiric Earth President Jen Vescio proposed that the biggest obstacle to physical AI is that the physical world has never been fully recorded. She said that Empiric Earth was formed by the merger of Nexar and Nauto and holds more than 10 billion miles of real driving data and 60 million edge cases, which can provide independent evaluation and validation for Physical AI. She emphasized that the company does not build cars or robots, but instead serves as a "referee" in the ecosystem, helping customers shorten development cycles, reduce risk, and accelerate commercialization. She also pointed out that physical-world data is difficult to record and highly fragmented, and that in U.S. data, for every crash there are about 19 near-collisions that go unrecorded.
AI-generated from public reports
Latest development · Report
Interview with Empiric Earth President Jen Vescio: Using 10 Billion Miles of Real Driving Data for Physical…Developments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 31
Unite.AI
Interview with Empiric Earth President Jen Vescio: Using 10 Billion Miles of Real Driving Data for Physical…
In the interview, Empiric Earth President Jen Vescio stated that the company was formed by the merger of Nexar and Nauto and holds over 10 billion miles of real driving data and 60 million edge cases, enabling it to provide independent evaluation and validation for Physical AI. She emphasized that the company does not build cars or robots, but instead serves as a "referee" in the ecosystem, helping customers shorten development cycles, reduce risk, and accelerate commercialization. She noted that physical-world data is difficult to record and highly fragmented, and that in U.S. data, for every crash there are about 19 near-collisions that go unrecorded.