A survey on imitation learning techniques for end-to-end autonomous vehicles
The state-of-the-art decision and planning approaches for autonomous vehicles have
moved away from manually designed systems, instead focusing on the utilisation of large …
moved away from manually designed systems, instead focusing on the utilisation of large …
A survey of end-to-end driving: Architectures and training methods
A Tampuu, T Matiisen, M Semikin… - … on Neural Networks …, 2020 - ieeexplore.ieee.org
Autonomous driving is of great interest to industry and academia alike. The use of machine
learning approaches for autonomous driving has long been studied, but mostly in the …
learning approaches for autonomous driving has long been studied, but mostly in the …
Model-based imitation learning for urban driving
An accurate model of the environment and the dynamic agents acting in it offers great
potential for improving motion planning. We present MILE: a Model-based Imitation …
potential for improving motion planning. We present MILE: a Model-based Imitation …
Trajectory-guided control prediction for end-to-end autonomous driving: A simple yet strong baseline
Current end-to-end autonomous driving methods either run a controller based on a planned
trajectory or perform control prediction directly, which have spanned two separately studied …
trajectory or perform control prediction directly, which have spanned two separately studied …
Rvs: What is essential for offline rl via supervised learning?
Recent work has shown that supervised learning alone, without temporal difference (TD)
learning, can be remarkably effective for offline RL. When does this hold true, and which …
learning, can be remarkably effective for offline RL. When does this hold true, and which …
Mp3: A unified model to map, perceive, predict and plan
High-definition maps (HD maps) are a key component of most modern self-driving systems
due to their valuable semantic and geometric information. Unfortunately, building HD maps …
due to their valuable semantic and geometric information. Unfortunately, building HD maps …
End-to-end autonomous driving: Challenges and frontiers
The autonomous driving community has witnessed a rapid growth in approaches that
embrace an end-to-end algorithm framework, utilizing raw sensor input to generate vehicle …
embrace an end-to-end algorithm framework, utilizing raw sensor input to generate vehicle …
Perceive, predict, and plan: Safe motion planning through interpretable semantic representations
In this paper we propose a novel end-to-end learnable network that performs joint
perception, prediction and motion planning for self-driving vehicles and produces …
perception, prediction and motion planning for self-driving vehicles and produces …
Advsim: Generating safety-critical scenarios for self-driving vehicles
As self-driving systems become better, simulating scenarios where the autonomy stack may
fail becomes more important. Traditionally, those scenarios are generated for a few scenes …
fail becomes more important. Traditionally, those scenarios are generated for a few scenes …
Urban driver: Learning to drive from real-world demonstrations using policy gradients
In this work we are the first to present an offline policy gradient method for learning imitative
policies for complex urban driving from a large corpus of real-world demonstrations. This is …
policies for complex urban driving from a large corpus of real-world demonstrations. This is …