Look Only Where You Plan for Real-Time End-to-End Urban Driving
Overview
This research presents LOWP, a compact driving planner that avoids constructing dense bird's-eye-view representations by using learnable queries to read camera features directly at projected 3D anchors and via viewing rays.
Generated from attributed reports · Updated 13 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · speed: 1.7 other · Basis not reported
“viewing rays, so no dense BEV is built and no object or map is supervised. Evaluations on open-loop nuScenes, pseudo-simulated NAVSIM and closed-loop Bench2Drive show competitive planning with a compact representation. On nuScenes, average L2 changes from 0.302 to 0.296 m with 53% of the dense counterpart's parameters and 1.7 times its speed on the same GPU; the anchor-based reader performs better on turns than the”
Exact source · revision 1Source owner not reported
Reported quantity · PDMS: 85.9 other · Basis not reported
“global reader. On NAVSIM, scoring the planner's own trajectories alongside a vocabulary gives 85.9 PDMS without retraining. The closed-loop control configuration scores 65.5 on 218 routes, with a brake-induced standstill failure whose release rule has an inconclusive aggregate benefit. We distinguish measured latency from hardware-transferred estimates, which do not establish a common-hardware ranking.”
Exact source · revision 1Source owner not reported
Reported quantity · score: 65.5 other · Basis not reported
“global reader. On NAVSIM, scoring the planner's own trajectories alongside a vocabulary gives 85.9 PDMS without retraining. The closed-loop control configuration scores 65.5 on 218 routes, with a brake-induced standstill failure whose release rule has an inconclusive aggregate benefit. We distinguish measured latency from hardware-transferred estimates, which do not establish a common-hardware ranking.”
Exact source · revision 1Source owner not reported
Reported quantity · routes: 218 other · reported trials
“global reader. On NAVSIM, scoring the planner's own trajectories alongside a vocabulary gives 85.9 PDMS without retraining. The closed-loop control configuration scores 65.5 on 218 routes, with a brake-induced standstill failure whose release rule has an inconclusive aggregate benefit. We distinguish measured latency from hardware-transferred estimates, which do not establish a common-hardware ranking.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalLook Only Where You Plan for Real-Time End-to-End Urban Driving
This research presents LOWP, a compact driving planner that avoids constructing dense bird's-eye-view representations by using learnable queries to read camera features directly at projected 3D anchors and via viewing rays.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).