Benchmark RadarDuoBench
DuoBench is a benchmarking framework for bimanual manipulation policies on the FR3 Duo platform, with eleven tasks across four coordination categories, simulated and partially real-world, plus human-teleoperated datasets. It proposes stage-based evaluation beyond binary success.
- Released
- 2026-06-10
- Readiness
- Inspectable
- Primary field
- Robotics & Autonomous Systems
Why it matters
Provides a reproducible testbed for diagnosing failures in dual-arm policy learning, covering coordination challenges not captured by existing benchmarks. Useful for robotics researchers working on bimanual manipulation.
Motivation
Bimanual robot systems substantially expand manipulation capabilities, but coordinating two arms introduces additional control complexity and failure modes that are not well captured by existing benchmarks.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.