Job Description

1. L2 Level Longitudinal and Lateral Planning and Control Algorithm Development: Responsible for the design of planning and control strategies for functions such as ACC (Adaptive Cruise Control), LKA (Lane Keeping Assist), TJA (Traffic Jam Assist), with a focus on optimizing driving comfort (e.g., jerk suppression, smooth cornering, smooth follow-to-stop/start).

2. Application of AI Methods in Comfort Optimization: Explore imitation learning, reinforcement learning, or lightweight end-to-end models to learn smooth throttle/brake/steering curves from human driving data, reducing the mechanical feel caused by rules.

3. Joint Balance of Comfort and Safety: While ensuring the priority of safety functions like AEB, optimize false triggers (e.g., false deceleration, unnecessary warnings) and overly aggressive interventions in daily driving to enhance user trust.

4. Integration of Functional Safety and Comfort Constraints: Design redundancy and monitoring mechanisms for control modules according to ISO 26262 (ASIL level requirements) to ensure smooth degradation in abnormal situations (e.g., sensor failure, signal frame loss) without abrupt actions.

5. Simulation and Real-Vehicle Closed-Loop Evaluation: Establish an automated evaluation system including comfort metrics (jerk, lateral acceleration rate of change, following error), driven by road test data for iterative improvements.

Qualifications

• Basic Requirements

  1. Bachelor's degree or above in Vehicle Engineering, Control Engineering, Computer Science, Automation, or related majors, with over 2 years of experience in L2 ADAS planning and control development.
  2. Proficient in C++/Python, familiar with Linux and embedded platforms (e.g., Infineon, NXP, TI TDA4, or Horizon Journey).
  3. Familiar with classic planning and control algorithms: PID, MPC, LQR, Pure Pursuit, Lattice Planner, or Dynamic Programming/Quadratic Programming.

• Bonus/Specific Requirements

  1. Experience in L2 function mass production (ACC, LKA, TJA) and led comfort tuning (e.g., curve speed control, smooth start/stop).
  2. Understanding of AI applications in planning and control: such as using behavioral cloning to optimize following strategies, or using reinforcement learning to learn lane change comfort parameters.
  3. Familiar with functional safety standards: understanding ASIL level classification, FFI analysis, and FMEA implementation in planning and control modules.
  4. Strong data-driven mindset: able to use large-scale road test logs for problem localization and regression testing.

Additional Information