Autonomous Motion Planning & Control Engineer - Logistics AGF Team

We are looking for a Motion Planning / Navigation Engineer to develop and deploy the algorithms that enable autonomous guided forklifts to plan, navigate, and move safely and accurately in real-world environments.

The ideal candidate has strong hands-on experience in path/motion planning, trajectory generation, trajectory tracking, and advanced control, with proven experience implementing and deploying MPC or equivalent controllers on real robots.

Experience with forklifts, AMRs, AGVs, autonomous vehicles, or warehouse robots is highly desirable.

Key Responsibilities

• Design, implement, and deploy global/local path planning and motion planning algorithms.
• Develop trajectory generation and optimization considering robot kinematic and dynamic constraints.
• Design, implement, and tune MPC or other advanced motion/trajectory controllers.
• Develop robust trajectory tracking and path-following for real-world robots.
• Implement obstacle avoidance, collision checking, and recovery behaviors.
• Handle constraints including turning radius, steering, velocity, acceleration, angular velocity, robot footprint, and actuator limits.
• Integrate planning and control with SLAM/localization, perception, odometry, and vehicle control systems.
• Develop and maintain navigation software using ROS/ROS2.
• Test and validate algorithms in simulation and on physical robots.
• Diagnose issues such as path deviation, oscillations, unstable motion, poor tracking, deadlocks, and inefficient trajectories.
• Optimize algorithms for accuracy, robustness, and real-time performance.

Required Qualifications

• Bachelor's/Master's degree in Robotics, Computer Science, Electrical/Mechanical Engineering, or related field.
• 3+ years of hands-on experience in motion planning, navigation, or control for mobile robots/autonomous systems.
• Strong understanding of path planning, motion planning, trajectory generation, and trajectory tracking.
• Proven hands-on experience implementing and deploying MPC or equivalent advanced motion controllers on real robots.
• Strong understanding of robot kinematics, coordinate transformations, and non-holonomic motion models.
• Experience with control approaches such as MPC, LQR, nonlinear control, Pure Pursuit, Stanley, or equivalent.
• Strong understanding of global/local planners, obstacle avoidance, and collision checking.
• Strong C++ skills; Python is a plus.
• Strong hands-on experience with ROS/ROS2, with ROS2 preferred.
• Experience integrating planning and control with perception, localization, and odometry.
• Experience debugging robotics systems using RViz/RViz2, logs, simulation, and real-robot testing.
• Strong Linux and Git experience.
• Ability to take algorithms from concept → implementation → simulation → real-world deployment.

Good to Have

• Experience with forklifts, AMRs, AGVs, autonomous vehicles, or warehouse robotics.
• Experience with forklift/steering-based or Ackermann kinematics.
• Experience with Nav2 / ROS2 Navigation Stack.
• Experience with A*, Hybrid A*, Dijkstra, RRT/RRT*, DWA, TEB, or similar planning approaches.
• Experience with trajectory optimization and constrained optimization.
• Experience optimizing algorithms for real-time embedded systems.
• Experience with Gazebo, Isaac Sim, or other robotics simulators.
• Experience with industrial robot safety and real-world autonomous deployment.

What We Are Looking For

We are looking for someone who understands how planning and control work under the hood, not someone who has only integrated existing navigation packages.

You should be able to diagnose a problem such as:

"The robot follows the planned path poorly, oscillates around the trajectory, or fails to navigate a constrained warehouse aisle."

and determine whether the root cause is planning, trajectory generation, kinematic constraints, controller design/tuning, localization, or actuation.

The candidate should be comfortable going beyond parameter tuning and modifying, optimizing, or developing planning and control algorithms when required.

Deep Planning & Control → Real-World Implementation → Reliable Autonomous Motion