ADO dynamically selects from a library of vehicle dynamics models for MPC by estimating terrain-specific accuracy via residual errors on counterfactual rollouts, reducing error versus fixed low-latency models while avoiding the cost of the highest-fidelity one.
Meta-learning online dynamics model adaptation in off-road autonomous driving,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Balancing Accuracy and Efficiency: Adaptive Dynamics Orchestration for Model Predictive Control
ADO dynamically selects from a library of vehicle dynamics models for MPC by estimating terrain-specific accuracy via residual errors on counterfactual rollouts, reducing error versus fixed low-latency models while avoiding the cost of the highest-fidelity one.