Motional

Quarterly Report filed 2026-04-30

Material Event filed 2026-04-30

TreeIRL: Safe Urban Driving with Tree Search and Inverse Reinforcement Learning mjohnson@weare… Tue, 04/28/2026 - 20:50 Authors: Momchil S. Tomov, Sang Uk Lee, Hansford Hendrago, Jinwook Huh, Teawon Han, Forbes Howington, Rafael da Silva, Gianmarco Bernasconi, Marc Heim, Samuel Findler, Xiaonan Ji, Alexander Boule, Michael Napoli, Kuo Chen, Jesse Miller, Boaz Floor, Yunqing Hu Published: Sept. 16, 2025 Summary: We present TreeIRL, a novel planner for autonomous driving that combines Monte Carlo tree search (MCTS) and inverse reinforcement learning (IRL) to achieve state-of-the-art performance in simulation and in real-world driving. The core idea is to use MCTS to find a promising set of safe candidate trajectories and a deep IRL scoring function to select the most human-like among them. We evaluate TreeIRL against both classical and state-of-the-art planners in large-scale simulations and on 500+ miles of real-world autonomous driving in the Las Vegas metropolitan area. Test scenarios

Lab2Car: A Versatile Wrapper for Deploying Experimental Planners in Complex Real-World Environments mjohnson@weare… Tue, 04/28/2026 - 20:48 Authors: Marc Heim, Francisco Suárez-Ruiz, Ishraq Bhuiyan, Bruno Brito, Momchil S. Tomov Published: May 19, 2025 Summary: Human-level autonomous driving is an ever-elusive goal, with planning and decision making - the cognitive functions that determine driving behavior - posing the greatest challenge. Despite a proliferation of promising approaches, progress is stifled by the difficulty of deploying experimental planners in naturalistic settings. In this work, we propose Lab2Car, an optimization-based wrapper that can take a trajectory sketch from an arbitrary motion planner and convert it to a safe, comfortable, dynamically feasible trajectory that the car can follow. This allows motion planners that do not provide such guarantees to be safely tested and optimized in real-world environments. We demonstrate the versatility of Lab2Car by using it to

DriveIRL: Drive in Real Life with Inverse Reinforcement Learning mjohnson@weare… Tue, 04/28/2026 - 20:23 Authors: Tung Phan-Minh, Forbes Howington, Ting-Sheng Chu, Momchil S. Tomov, Robert E. Beaudoin, Sang Uk Lee, Nanxiang Li, Caglayan Dicle, Samuel Findler, Francisco Suarez-Ruiz, Bo Yang, Sammy Omari, Eric M. Wolff Published: May 29, 2023 Summary: In this paper, we introduce the first published planner to drive a car in dense, urban traffic using Inverse Reinforcement Learning (IRL). Our planner, DriveIRL, generates a diverse set of trajectory proposals and scores them with a learned model. The best trajectory is tracked by our self-driving vehicle's low-level controller. We train our trajectory scoring model on a 500+ hour real-world dataset of expert driving demonstrations in Las Vegas within the maximum entropy IRL framework. DriveIRL's benefits include: a simple design due to only learning the trajectory scoring function, a flexible and relatively interpretable feature engineerin

Motional Robotaxis Now Available on Uber in Las Vegas mjohnson@weare… Tue, 04/21/2026 - 14:46 Beginning today, everyone has the chance to catch a ride in a Motional Robotaxi on the @Uber ride hail network in Las Vegas, all you need is the Uber app on your phone to be able to get matched with our Robotaxis. I am so proud to have @Motional Robotaxis available to the public again.  We have always had a strong operational capability, giving more than 130,000 rides to the public in total so far and this experience has taught us a lot. We are looking forward to building on that experience with this supervised service phase to capture customer feedback - from users who ride with us through our partnership with Uber. That feedback is essential to ensuring we have a very comfortable and seamless robotaxi experience before we transition to rider-only later this year.  We are now providing autonomous rides with our all-new AI-first autonomous driving system, which is the result of refoc

Daekwon Ko mjohnson@weare… Thu, 04/02/2026 - 13:19 Daekwon Ko is the Chief Financial Officer at Motional.  Daekwon brings decades of finance and global leadership experience to the Motional team, most recently serving as the Chief Financial Officer for Hyundai Motor Asia Pacific Regional Headquarters.  He has held numerous other senior management roles at Hyundai Motor Company across diverse financial areas, including leading global FP&A as the Head of the Global Business Management Group and Corporate Debt & Treasury Management as the Treasury Team Leader.  Daekwon holds a Master of Public Administration from Seoul National University and graduated with a Bachelor of Arts in Economics from Yonsei University. 

Phil Michel mjohnson@weare… Thu, 04/02/2026 - 13:15 Phil Michel is the Senior Vice President of Autonomy & AI at Motional, responsible for the science, engineering, and strategic direction behind Motional’s autonomous driving technology.  Previously, Phil held senior technical leadership roles at Cruise and General Motors, driving AI strategy and execution across autonomy, simulation, data, and testing. Phil also led autonomy science, engineering, and product teams at Amazon, helping scale autonomous delivery across four U.S. states. He built Toyota Research Institute’s machine learning organization, advised Toyota Motor Corporation on global AI strategy, and developed advanced robotic perception systems at Google/X. He also served as a Project Assistant Professor at the University of Tokyo. Phil began his career in finance as a derivatives trader and spent seven years at Goldman Sachs in Tokyo trading index volatility before going on to lead quantitative volatility trading ac

Proxy Statement filed 2026-04-02

Uber and Motional Launch Robotaxi Service in Las Vegas lflanagan@wear… Thu, 03/12/2026 - 18:29 Starting today, Uber Technologies, Inc. (NYSE: UBER) and Motional, a leader in autonomous vehicle technology that is majority owned by Hyundai Motor Group, announced that Uber riders in Las Vegas can now be matched with an all-electric Motional IONIQ 5 robotaxi — unlocking an exciting new way to hit the jackpot on the Strip. At launch, the service will be available at designated locations along Las Vegas Boulevard, including rideshare zones at the Resorts World Las Vegas and Encore at the Wynn Las Vegas — plus Westgate Las Vegas Resort & Casino and curbside in Downtown Las Vegas and throughout the Town Square shopping district near the airport – with plans to expand the operating area in the future. Here’s what riders can expect when matched with a Motional robotaxi on Uber: Request a ride : Riders who request an UberX, Uber Electric, Uber Comfort, or Uber Comfort Electric may be matched

Liability Waiver for Rides mjohnson@weare… Wed, 03/04/2026 - 22:13 Liability Waiver for Rides LIMITATION OF LIABILITY, ASSUMPTION OF RISK, INDEMNITY AND ARBITRATION AGREEMENT (“AGREEMENT”) This Agreement describes the terms and conditions (“Terms”) pursuant to which Motional AD Inc. together with its subsidiaries and affiliates, and each of its and their respective officers, directors, partners, suppliers, licensors, and employees (individually and collectively, “Motional”) offers you access to Motional’s autonomous vehicles. In consideration of the opportunity to ride in a Motional autonomous vehicle (the “Services”), you agree to these Terms. Uber Technologies, Inc. (“Uber”) owns and operates the Uber platform, and all of the Terms of Service you agreed to with Uber remain in effect and are hereby incorporated by reference including all provisions related to dispute resolution.  Specifically, you have agreed to an Arbitration Agreement which waives your right to have any dispute