… skills. Inspired by motion planning in autonomous driving, we propose to exploit motion skills
in … and thus generalizable to complex driving tasks. Fig. 1(b) depicts that with such naturally-…

… In this work, we present a skill-based framework that … Specifically, we design a variational
autoencoder (VAE) to learn skills … of the complex driving skills. The final policy treats learned …

… into account, an autonomous driving vehicle can acquire significant social skills. The …
The acquired SVO is parameterized to adjust cost structure in the Stackelberg game model, …

… combines the notion of parameterized skills [3, 4] with end-toend deep visuomotor skills from
… Parameterized skill learning as described by da Silva et al. [3] aims to learn a mapping from …

Steering control for autonomous vehicles at high speeds is challenging due to the highly
nonlinear vehicle dynamics. The traditional model-based controllers usually degrade …

… It even gets worse as we attempt to tackle increasingly demanding and diverse problems in
autonomous driving, such as crossing an unsignalized intersection or doing an unprotected …

… In contrast, using our parameterized model to retrace and analyze each accident, the number
of recovery actions obtained can be multiple orders of magnitude higher. Subsequently, …

… and accident-prone urban traffic scenarios for autonomous driving wherein making safe
and … RL algorithm to solve a control policy parameterized by NN which is capable of tracking …

We propose and demonstrate a framework called perception as prediction for autonomous
driving that uses general value functions (GVFs) to learn predictions. Perception as prediction …

… While behavior cloning has recently emerged as a highly successful paradigm for
autonomous driving humans rarely learn to perform complex tasks such as driving via imitation or …