LEARNINGCURRENT2026-06-17

Constant Time-Delay Leader Following with Neural Networks and Invariant Extended Kalman Filters for Arbitrary Trajectories

Luka Antonyshyn, Paulo Ricardo Marques de Araujo, Sidney Givigi

This paper enables Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. vehicle convoys to follow a leader through time-delayed observations without GPS, communication, or a shared coordinate system by combining neural networks with Kalman filtering and geometric Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans.. You get accurate Core ConceptsTrajectoryA sequence of states or actions over time. prediction and Control & PlanningControlThe method used to make the robot move the way you want. even with long delays and arbitrary leader motions.

THE PROBLEM

This paper focuses on learning. Proposes a hybrid approach combining Seq2Seq neural networks, invariant extended Kalman filters (IEKF), and geometric Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. for multi-vehicle convoy following under constant time delays without inter-vehicle communication or global positioning. Validated in Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested. and with real robots. Read the paper by tracking the Core ConceptsTaskThe job the robot is supposed to complete, such as pick-and-place, navigation, or drawer opening. definition, the Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. or data assumptions, and the evidence that supports the claimed improvement.

HOW IT WORKS

1

Task framing

The paper frames the work as learning. Start here because it defines what success means and which assumptions the rest of the method inherits.

2

Core method

This paper enables Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. vehicle convoys to follow a leader through time-delayed observations without GPS, communication, or a shared coordinate system by combining neural networks with Kalman filtering and geometric Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans.. You get accurate Core ConceptsTrajectoryA sequence of states or actions over time. prediction and Control & PlanningControlThe method used to make the robot move the way you want. even with long delays and arbitrary leader motions. When reading the method section, identify the inputs, the learned or engineered representation, and the Core ConceptsActionA command the robot sends to its motors, controller, or low-level system. or prediction produced by the system.

3

Data and supervision

For robotics work, the data story is part of the method: check whether the system depends on Imitation & Reinforcement LearningTeleoperation (teleop)A human remotely controlling the robot, often to collect demonstrations., Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested., internet video, human labels, or Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. rollouts.

4

Evaluation evidence

The paper should be judged through its Simulation & Sim-to-RealEvaluationMeasuring how well a robot system performs. protocol: what data is used, what Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. or simulator is tested, and which Evaluation & ResearchBaselineA reference method used for comparison. comparisons support the claim. Look for the gap between the headline result and the Simulation & Sim-to-RealDeploymentPutting the trained system on a real robot. setting you would actually care about.

KEY RESULTS

Main contributionConceptual contribution

This paper enables Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. vehicle convoys to follow a leader through time-delayed observations without GPS, communication, or a shared coordinate system by combining neural networks with Kalman filtering and geometric Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans.. You get accurate Core ConceptsTrajectoryA sequence of states or actions over time. prediction and Control & PlanningControlThe method used to make the robot move the way you want. even with long delays and arbitrary leader motions.

WHY DEVELOPERS SHOULD CARE

This paper enables Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. vehicle convoys to follow a leader through time-delayed observations without GPS, communication, or a shared coordinate system by combining neural networks with Kalman filtering and geometric Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans.. You get accurate Core ConceptsTrajectoryA sequence of states or actions over time. prediction and Control & PlanningControlThe method used to make the robot move the way you want. even with long delays and arbitrary leader motions.

LIMITATIONS

The main limitation to check is whether the claimed behavior holds outside the paper's reported setup. That means testing across different Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. embodiments, scenes, objects, and data distributions.

WHAT COMES NEXT

The practical next step is independent reproduction with clear baselines, ablations, and stress tests. For a developer, the useful follow-up is to map the paper's learning assumptions onto a concrete Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. stack, then test the smallest version of the method that could run end to end.

RELATED PAPERS