Sim-to-Real Transfer

Sim-to-real transfer — training policies in simulation and deploying on physical hardware — is the bridge between unlimited virtual data and messy reality. Domain randomization (Tobin et al., 2017) was the first scalable approach, and OpenAI's Rubik's cube hand (2019) showed it could work for dexterous manipulation. The modern toolkit combines photorealistic rendering (Isaac Sim, MuJoCo MJX on GPU), system identification, and real-world fine-tuning, but the gap persists for contact-rich tasks where simulation physics diverge from reality. Narrowing this gap is existential for robotics — it determines whether lab results actually work in factories and homes.

1
Datasets
3
Results
driving_score
Canonical metric
Canonical Benchmark

CARLA Leaderboard

Official CARLA Autonomous Driving Leaderboard evaluating end-to-end driving policies trained in simulation across diverse routes, weather, and traffic. Primary metric is Driving Score (DS = Route Completion × Infraction Penalty). Widely used as the de-facto sim-to-real/sim-to-sim benchmark for learned driving policies.

Primary metric: driving_score
View full leaderboard

Top 10

Leading models on CARLA Leaderboard.

RankModeldriving_scoreYearSource
1
InterFuser
76.22026paper
2
TCP
75.12026paper
3
Think2Drive
46.02026paper

All datasets

1 dataset tracked for this task.

Related tasks

Other tasks in Robots.