JRDB-AVR: An Active Visual Reasoning Benchmark for Embodied Agents in Real-World Environments
JRDB-AVR is introduced, a benchmark derived from existing real-world JRDB robotics data through a structured question-generation engine that turns this gap between answer accuracy and evidence accuracy in current baselines into an explicit evaluation.
Zhixi Cai, Fu-Cai Ke, Sukai Huang et al.
· 0 citations