Xin-Zhe Chen

AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic Manipulation

AffordSim is introduced, a scalable data generator and benchmark that integrates open-vocabulary 3D affordance prediction into simulation-based trajectory generation and achieves 93% of the trajectory collection success rate of manual contact annotations on affordance-critical tasks and 89% on hard composite tasks.