Parting with Misconceptions about Learning-based Vehicle Motion Planning. (arXiv:2306.07962v2 [cs.RO] UPDATED)

The release of nuPlan marks a new era in vehicle motion planning research,
offering the first large-scale real-world dataset and evaluation schemes
requiring both precise short-term planning and long-horizon ego-forecasting.
Existing systems struggle to simultaneously meet both requirements. Indeed, we
find that these tasks are fundamentally misaligned and should be addressed
independently. We further assess the current state of closed-loop planning in
the field, revealing the limitations of learning-based methods in complex
real-world scenarios and the value of simple rule-based …

arxiv dataset evaluation forecasting indeed motion planning planning release requirements research scale struggle systems tasks world