ﻻ يوجد ملخص باللغة العربية
How to explore corner cases as efficiently and thoroughly as possible has long been one of the top concerns in the context of deep reinforcement learning (DeepRL) autonomous driving. Training with simulated data is less costly and dangerous than utilizing real-world data, but the inconsistency of parameter distribution and the incorrect system modeling in simulators always lead to an inevitable Sim2real gap, which probably accounts for the underperformance in novel, anomalous and risky cases that simulators can hardly generate. Domain Randomization(DR) is a methodology that can bridge this gap with little or no real-world data. Consequently, in this research, an adversarial model is put forward to robustify DeepRL-based autonomous vehicles trained in simulation to gradually surfacing harder events, so that the models could readily transfer to the real world.
In the past decades, we have witnessed significant progress in the domain of autonomous driving. Advanced techniques based on optimization and reinforcement learning (RL) become increasingly powerful at solving the forward problem: given designed rew
Producing agents that can generalize to a wide range of visually different environments is a significant challenge in reinforcement learning. One method for overcoming this issue is visual domain randomization, whereby at the start of each training e
We present fully autonomous source seeking onboard a highly constrained nano quadcopter, by contributing application-specific system and observation feature design to enable inference of a deep-RL policy onboard a nano quadcopter. Our deep-RL algorit
Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and fine-tuning the w
This paper employs correct-by-construction control synthesis, in particular controlled invariant set computations, for falsification. Our hypothesis is that if it is possible to compute a large enough controlled invariant set either for the actual sy