作者位次 #2/5IROS 2026Poster· Imitation and Demonstration Learning for Robot Skills
DiffOG: Differentiable Policy Trajectory Optimization with Generalizability
Zhengtong Xu · Zichen Miao · Qiang Qiu · Zhe Zhang · Yu She
理论与学习动力学Deep Learning in Robotics and AutomationLearning from DemonstrationDexterous ManipulationDifferentiable OptimizationOpenReview