论文标题
重新思考SIM2REAL：较低的保真度模拟导致导航中的SIM2REAL转移更高
Rethinking Sim2Real: Lower Fidelity Simulation Leads to Higher Sim2Real Transfer in Navigation
论文作者
论文摘要
如果我们想在现实中部署它们之前在模拟中训练机器人，那么假定减少SIM2REAL差距的人似乎很自然，并且几乎是不言而喻的，涉及创建增加忠诚度的模拟器（因为现实就是事实）。我们挑战了这一假设，并提出了相反的假设-SIM2REAL转移机器人可以通过较低（不是更高）的保真度模拟来改善。我们使用3种不同的机器人（A1，Aliengo，Spot）对这一假设进行了系统的大规模评估 - 在现实世界中以及2个不同的模拟器（栖息地和Igibson）。我们的结果表明，与期望相反，增加忠诚无助于学习；由于模拟速度缓慢（防止大规模学习）和对模拟物理学不准确的过度拟合，因此性能很差。取而代之的是，使用现实世界数据构建机器人运动的简单模型可以改善学习和概括。
If we want to train robots in simulation before deploying them in reality, it seems natural and almost self-evident to presume that reducing the sim2real gap involves creating simulators of increasing fidelity (since reality is what it is). We challenge this assumption and present a contrary hypothesis -- sim2real transfer of robots may be improved with lower (not higher) fidelity simulation. We conduct a systematic large-scale evaluation of this hypothesis on the problem of visual navigation -- in the real world, and on 2 different simulators (Habitat and iGibson) using 3 different robots (A1, AlienGo, Spot). Our results show that, contrary to expectation, adding fidelity does not help with learning; performance is poor due to slow simulation speed (preventing large-scale learning) and overfitting to inaccuracies in simulation physics. Instead, building simple models of the robot motion using real-world data can improve learning and generalization.
