R&D-036 Robotics Control Engineer (Low-Level / Motor control)

About this role

※日本語版が続きます。 About AIRoA AI Robot Association (AIRoA) is an organization dedicated to collecting large-scale real-world robot data, including data from humanoid robots, and advancing the development of generative AI foundation models in the field of robotics. AIRoA has been selected by Japan’s Ministry of Economy, Trade and Industry (METI) and NEDO as an implementing organization for the development of a data platform for generative AI foundation models in robotics under the “Post-5G Information and Communication Systems Infrastructure Enhancement R&D Project.” The project budget is JPY 20.5 billion. Based on this foundation, AIRoA is working on a project to collect one million hours of humanoid robot operation data using more than 100 robots, and to develop a world-class Vision-Language-Action (VLA) model by leveraging this data. Role Overview This position is responsible for designing, implementing, and tuning low-level control systems that translate motion commands generated by higher-level control layers into precise and reliable torque and motion for the joint actuators of humanoid and dual-arm robots. You will work primarily at the layer closest to motor control, including field-oriented control (FOC) for brushless motors; current, torque, velocity, and position control loops; motor-control-board bring-up; sensor calibration; and implementation of safety mechanisms. Rather than high-level (meta) control such as Motion Planning or Navigation, you will take end-to-end ownership of actuator-level control firmware, from prototype through mass production. This role supports the lowest layer of the control stack and serves as the bridge that ensures the motions required by the Whole-Body Control and AI/ML teams are realized reliably on physical hardware. Responsibilitie Design, implement, and tune FOC (vector control) for brushless actuators, current and torque control loops based on dq transformation, and velocity and position control loops. Bring up and debug custom motor-control boards and sensors. Build calibration and synchronization pipelines for encoders and current/voltage measurements. Implement actuator safety mechanisms, including overcurrent, overtemperature, watchdog, and brownout protection. Design control loops under real-time constraints using low-level peripherals such as timers, ADC, PWM, and DMA. Implement communication interfaces such as CAN (FD) and EtherCAT, and design interfaces with higher-level software platforms. Develop diagnostic and logging mechanisms for torque, current, temperature, error states, and other signals to support fault detection during operation on physical hardware. Collaborate with the Whole-Body Control and AI/ML teams on force and compliance control under dynamic loads. Continuously improve control performance through on-hardware validation and parameter tuning. AIRoAについて AI Robot Association（AIRoA）は、ヒューマノイドロボットをはじめとする実世界ロボットの⼤規模データを収集し、ロボティクス分野における⽣成AI基盤モデルの開発を推進する組織です。 AIRoAは、経済産業省およびNEDOの「ポスト5G情報通信システム基盤強化研究開発事業」において、ロボティクス分野の⽣成AI基盤モデル開発に向けたデータプラットフォーム開発の採択事業者に決定しており、事業予算は205億円です。この基盤をもとに、100台以上のロボットを⽤いて100万時間規模のヒューマノイドロボット操作データを収集し、それを活⽤して世界最⾼⽔準のVision-Language-Action（VLA）モデルを開発するプロジェクトを進めています。 募集概要 本ポジションは、ヒューマノイドや双腕ロボットの関節アクチュエータについて、上位の制御層が⽣成する動作指令を、精密かつ信頼性の⾼いトルク‧動作へと変換する低レベル制御システムの設計‧実装‧チューニングを担うポジションです。ブラシレスモータのベクトル制御（FOC）や電流‧トルク‧速度‧位置の各制御ループ、モータ制御基板のブリングアップ、センサ校正、安全機構の実装など、モータ制御に最も近いレイヤを中⼼的に担当していただきます。 Motion PlanningやNavigationといった⾼レベル（メタ）な制御ではなく、その⼟台となるアクチュエータレベルの制御ファームウェアを、プロトタイプから量産まで⼀貫してオーナーシップを持って開発します。全⾝制御（Whole-Body Control）チームやAI∕MLチームが求める動作を、実機のハードウェア上で確実に実現するための橋渡しを担う、制御スタックの最下層を⽀える役割です。 業務内容 ブラシレスアクチュエータ向けのFOC（ベクトル制御）、dq変換に基づく電流‧トルク制御ループ、および速度‧位置制御ループの設計‧実装‧チューニング カスタムモータ制御基板およびセンサのブリングアップとデバッグ エンコーダ、電流∕電圧計測のキャリブレーション‧同期パイプラインの構築 過電流‧過熱‧ウォッチドッグ‧ブラウンアウト保護など、アクチュエータの安全機構の実装 タイマ∕ADC∕PWM∕DMA等の低レベルペリフェラルを活⽤した、リアルタイム制約下での制御ループ設計 CANFD、EtherCAT等の通信インターフェースの実装と、上位ソフトウェア基盤とのインターフェース設計 実機運⽤時の故障検出に向けた、トルク‧電流‧温度‧エラー状態などの診断‧ロギング機構の開発 動的負荷下での⼒‧コンプライアンス制御に向けた、全⾝制御‧AI∕MLチームとの協働 実機での動作検証‧パラメータチューニングによる制御性能の継続的な改善 Requirements ※日本語版が続きます。 Required Qualifications Professional experience with at least one of the following: robotic arms, robotic hands, or humanoid robots. At least 3 years of professional experience in real-time embedded software development, including microcontrollers, device drivers, and low-level libraries. Strong proficiency in C/C++, with experience implementing low-level peripherals such as timers, ADC, PWM, DMA, and non-volatile memory. Practical knowledge of motor-control theory, including FOC/vector control and dq transformation, and experience designing and implementing current, torque, velocity, and position control loops. Experience working with encoders and current/voltage sensors, including calibration and synchronization. Experience implementing or debugging physical hardware using communication interfaces such as SPI, UART, CAN (FD), RS-485, and EtherCAT. Experience implementing actuator safety mechanisms such as overcurrent, overtemperature, watchdog, and brownout protection. Business level Japanese Preferred Qualifications Experience developing and shipping motor-control firmware from prototype through mass production. Experience with brushless DC motors, servo motors, and actuator control. Understanding of RTOS concepts and hands-on implementation experience. Experience with motion control using EtherCAT, CANopen, CiA 402, or similar technologies. Knowledge of real-time control, control-cycle design, latency reduction, and jitter reduction. Experience coordinating with the Whole-Body Control layer for torque control, impedance control, admittance control, or similar methods. Experience using Python or similar tools for log analysis, validation automation, and test-tool development. Experience designing and validating control models using MATLAB/Simulink or similar tools. Experience using physics simulators such as MuJoCo, Isaac, or Pinocchio. Ability to read technical documentation in English and experience