TerraTransfer++: Demonstration-Free End-to-End Planner
Overview
TerraTransfer++ is a demonstration-free end-to-end planner for autonomous driving that uses self-play in vectorized simulators to generate diverse and reactive policies. The method pretrains a single policy through self-play, distills its rollouts into a trajectory teacher, and trains lightweight adapters on a frozen vision backbone to reproduce the latent space of the teacher. The approach achieves strong performance on benchmark tasks such as HUGSim and NAVSIM without requiring human demonstrations.
From arXiv Robotics — research abstracts
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 · end-to-end performance: 59.4 other · Basis not reported · Differing source assertions
“itation-based end-to-end method on the photorealistic 3D Gaussian splatting closed-loop benchmark HUGSim, and a planner that reaches 59.4 EPDMS on NAVSIM navhard, above every published method including DriveZero-Scale (57.1), and 95.5 PDMS on navtest, without human demonstrations.”
Exact source · revision 1Source owner not reported
Reported quantity · end-to-end performance: 95.5 other · Basis not reported · Differing source assertions
“itation-based end-to-end method on the photorealistic 3D Gaussian splatting closed-loop benchmark HUGSim, and a planner that reaches 59.4 EPDMS on NAVSIM navhard, above every published method including DriveZero-Scale (57.1), and 95.5 PDMS on navtest, without human demonstrations.”
Exact source · revision 1Source owner not reported
Reported quantity · end-to-end performance: 57.1 other · Basis not reported · Differing source assertions
“itation-based end-to-end method on the photorealistic 3D Gaussian splatting closed-loop benchmark HUGSim, and a planner that reaches 59.4 EPDMS on NAVSIM navhard, above every published method including DriveZero-Scale (57.1), and 95.5 PDMS on navtest, without human demonstrations.”
Exact source · revision 1Source owner not reported
Evidence dependency changes (2)
- 2026-10-30T20:38:36.491Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T20:38:14.839Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalTerraTransfer++: Demonstration-Free End-to-End Planner
TerraTransfer++ is a demonstration-free end-to-end planner for autonomous driving that uses self-play in vectorized simulators to generate diverse and reactive policies. The method pretrains a single policy through self-play, distills its rollouts into a trajectory teacher, and trains lightweight adapters on a frozen vision backbone to reproduce the latent space of the teacher. The approach achieves strong performance on benchmark tasks such as HUGSim and NAVSIM without requiring human demonstrations.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).