STEADY: Simultaneous State Estimation and Dynamics Learning from Indirect Observations

Accurate kinodynamic models play a crucial role in many robotics applications such as off-road navigation and high-speed driving. Many state-of-the-art approaches for learning stochastic kinodynamic models, however, require precise measurements of robot states as labeled input/output examples, which can be hard to obtain in outdoor settings due to limited sensor capabilities and the absence of ground truth. In this work, we propose a new technique for learning neural stochastic kinodynamic models from noisy and indirect observations by performing simultaneous state estimation and dynamics learning. The proposed technique iteratively improves the kinodynamic model in an expectation-maximization loop, where the E Step samples posterior state trajectories using particle filtering, and the M Step updates the dynamics to be more consistent with the sampled trajectories via stochastic gradient ascent. We evaluate our approach on both simulation and real-world benchmarks and compare it with several baseline techniques. Our approach not only achieves significantly higher accuracy but is also more robust to observation noise, thereby showing promise for boosting the performance of many other robotics applications.

Authors

• Jiayi Wei
• Jarrett Holtz
• Isil Dillig
• Joydeep Biswas

Keywords

• Navigation
• Filtering
• Stochastic processes
• Benchmark testing
• Robot sensing systems
• Boosting
• Trajectory
• Dynamic Conditions
• Simultaneous Estimation
• Indirect Observation
• Accuracy Of Model
• Stochastic Model
• Particle Filter
• Robotic Applications
• State Trajectories
• Observation Noise
• Noisy Observations
• Robot State
• Sample Trajectories
• Neural Network
• Time Step
• Learning Models
• Dynamic Model
• Posterior Probability
• Supervised Learning
• Large Uncertainties
• Latent Space
• Simultaneous Localization And Mapping
• Monte Carlo Error
• Maximum A Posteriori
• Early Stage Of Training
• Prediction Step
• Ground Truth Trajectory
• Control Sequence
• Network Inference
• Motion Capture
• Gradient Step