Belief-Space Planning with Planner-Conditioned Estimator Error under Intermittent Observations

Key points

• Belief-space planners with separately designed or off-the-shelf estimators may have access to state-relevant information the estimator does not observe.1
• When future corrections are intermittent and stochastic, differences between accepted and rejected error means introduce additional uncertainty terms to correction events that zero-mean assumptions ignore.1
• We evaluate the approach in simulation for a tilt-rotor VTOL landing on a ship deck using receding-horizon planning.1
• We find that conditioning on planner information reduced error-prediction loss for a command-blind EKF by 13.4% relative to a planner-ignorant model, with strongly regime and horizon-dependent forecasting abilities.1

Sources (1)

• [1]Belief-Space Planning with Planner-Conditioned Estimator Error under Intermittent Observations
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 11:08 PM

  In this paper, we propose a belief-space planning approach that predicts, propagates, and penalizes planner-conditioned estimator error along evaluated trajectories.

  Belief-space planners with separately designed or off-the-shelf estimators may have access to state-relevant information the estimator does not observe.

Extractive summary: sentences quoted from the sources.