LEARNING2026-04-15

UNRIO: Uncertainty-Aware Velocity Learning for Radar-Inertial Odometry

Jui-Te Huang, Tinashu Huang, Anthony Rowe, Michael Kaess

This paper presents a neural network-based approach to Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. odometry (determining a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions.'s position and motion) using radar and IMU sensors. Instead of using traditional signal processing pipelines on radar data, the authors train a deep learning model to directly interpret raw radar signals to estimate the Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions.'s Movement, Mechanics & Robot BodyVelocityHow fast something moves.. The key innovation is that their system also predicts uncertainty estimates for its predictions, which is crucial for robotics because it lets downstream Control & PlanningPlanningFiguring out what the robot should do before or during movement. and Control & PlanningControlThe method used to make the robot move the way you want. systems know when to trust the Movement, Mechanics & Robot BodyVelocityHow fast something moves. estimates. This is particularly useful in situations where traditional radar processing fails, like when a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. moves sideways. For developers, this demonstrates how neural networks can replace hand-tuned engineering in Perception & SensingSensorA device that provides information about the robot or its environment. fusion pipelines while providing the uncertainty quantification needed for safe Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. operation.

THE PROBLEM

This paper focuses on learning. This paper presents a neural network-based approach to Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. odometry (determining a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions.'s position and motion) using radar and IMU sensors. Instead of using traditional signal processing pipelines on radar data, the authors train a deep learning model to directly interpret raw radar signals to estimate the Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions.'s Movement, Mechanics & Robot BodyVelocityHow fast something moves.. The key innovation is that their system also predicts uncertainty estimates for its predictions, which is crucial for robotics because it lets downstream Control & PlanningPlanningFiguring out what the robot should do before or during movement. and Control & PlanningControlThe method used to make the robot move the way you want. systems know when to trust the Movement, Mechanics & Robot BodyVelocityHow fast something moves. estimates. This is particularly useful in situations where traditional radar processing fails, like when a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. moves sideways. For developers, this demonstrates how neural networks can replace hand-tuned engineering in Perception & SensingSensorA device that provides information about the robot or its environment. fusion pipelines while providing the uncertainty quantification needed for safe Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. operation. 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 presents a neural network-based approach to Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. odometry (determining a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions.'s position and motion) using radar and IMU sensors. Instead of using traditional signal processing pipelines on radar data, the authors train a deep learning model to directly interpret raw radar signals to estimate the Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions.'s Movement, Mechanics & Robot BodyVelocityHow fast something moves.. The key innovation is that their system also predicts uncertainty estimates for its predictions, which is crucial for robotics because it lets downstream Control & PlanningPlanningFiguring out what the robot should do before or during movement. and Control & PlanningControlThe method used to make the robot move the way you want. systems know when to trust the Movement, Mechanics & Robot BodyVelocityHow fast something moves. estimates. This is particularly useful in situations where traditional radar processing fails, like when a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. moves sideways. For developers, this demonstrates how neural networks can replace hand-tuned engineering in Perception & SensingSensorA device that provides information about the robot or its environment. fusion pipelines while providing the uncertainty quantification needed for safe Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. operation. 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 presents a neural network-based approach to Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. odometry (determining a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions.'s position and motion) using radar and IMU sensors. Instead of using traditional signal processing pipelines on radar data, the authors train a deep learning model to directly interpret raw radar signals to estimate the Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions.'s Movement, Mechanics & Robot BodyVelocityHow fast something moves.. The key innovation is that their system also predicts uncertainty estimates for its predictions, which is crucial for robotics because it lets downstream Control & PlanningPlanningFiguring out what the robot should do before or during movement. and Control & PlanningControlThe method used to make the robot move the way you want. systems know when to trust the Movement, Mechanics & Robot BodyVelocityHow fast something moves. estimates. This is particularly useful in situations where traditional radar processing fails, like when a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. moves sideways. For developers, this demonstrates how neural networks can replace hand-tuned engineering in Perception & SensingSensorA device that provides information about the robot or its environment. fusion pipelines while providing the uncertainty quantification needed for safe Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. operation.

WHY DEVELOPERS SHOULD CARE

This paper presents a neural network-based approach to Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. odometry (determining a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions.'s position and motion) using radar and IMU sensors. Instead of using traditional signal processing pipelines on radar data, the authors train a deep learning model to directly interpret raw radar signals to estimate the Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions.'s Movement, Mechanics & Robot BodyVelocityHow fast something moves.. The key innovation is that their system also predicts uncertainty estimates for its predictions, which is crucial for robotics because it lets downstream Control & PlanningPlanningFiguring out what the robot should do before or during movement. and Control & PlanningControlThe method used to make the robot move the way you want. systems know when to trust the Movement, Mechanics & Robot BodyVelocityHow fast something moves. estimates. This is particularly useful in situations where traditional radar processing fails, like when a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. moves sideways. For developers, this demonstrates how neural networks can replace hand-tuned engineering in Perception & SensingSensorA device that provides information about the robot or its environment. fusion pipelines while providing the uncertainty quantification needed for safe Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. operation.

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