相关论文: Query-Efficient Imitation Learning for End-to-End …

Autonomous driving in multi-agent dynamic traffic scenarios is challenging: the behaviors of road users are uncertain and are hard to model explicitly, and the ego-vehicle should apply complicated negotiation skills with them, such as…

Recently, diffusion policy has shown impressive results in handling multi-modal tasks in robotic manipulation. However, it has fundamental limitations in out-of-distribution failures that persist due to compounding errors and its limited…

Autonomous driving is a multi-agent setting where the host vehicle must apply sophisticated negotiation skills with other road users when overtaking, giving way, merging, taking left and right turns and while pushing ahead in unstructured…

As the advanced driver assistance system (ADAS) functions become more sophisticated, the strategies that properly coordinate interaction and communication among the ADAS functions are required for autonomous driving. This paper proposes a…

The ability to accurately predict and simulate human driving behavior is critical for the development of intelligent transportation systems. Traditional modeling methods have employed simple parametric models and behavioral cloning. This…

Driving in a dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision-making policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level…

Safeguard functions such as those provided by advanced emergency braking (AEB) can provide another layer of safety for autonomous vehicles (AV). A smart safeguard function should adapt the activation conditions to the driving policy, to…

Precise parking requires an end-to-end system where perception adaptively provides policy-relevant details - especially in critical areas where fine control decisions are essential. End-to-end learning offers a unified framework by directly…

A common failure mode for policies trained with imitation is compounding execution errors at test time. When the learned policy encounters states that are not present in the expert demonstrations, the policy fails, leading to degenerate…

Developing agents for complex and underspecified tasks, where no clear objective exists, remains challenging but offers many opportunities. This is especially true in video games, where simulated players (bots) need to play realistically,…

Deep reinforcement learning is actively used for training autonomous car policies in a simulated driving environment. Due to the large availability of various reinforcement learning algorithms and the lack of their systematic comparison…

Data-driven simulators promise high data-efficiency for driving policy learning. When used for modelling interactions, this data-efficiency becomes a bottleneck: Small underlying datasets often lack interesting and challenging edge cases…

End-to-end autonomous driving has made impressive progress in recent years. Existing methods usually adopt the decoupled encoder-decoder paradigm, where the encoder extracts hidden features from raw sensor data, and the decoder outputs the…

Existing end-to-end autonomous driving methods typically rely on imitation learning (IL) but face a key challenge: the misalignment between open-loop training and closed-loop deployment. This misalignment often triggers driver-initiated…

Autonomous driving has the potential to revolutionize mobility and is hence an active area of research. In practice, the behavior of autonomous vehicles must be acceptable, i.e., efficient, safe, and interpretable. While vanilla…

We present research using the latest reinforcement learning algorithm for end-to-end driving without any mediated perception (object recognition, scene understanding). The newly proposed reward and learning strategies lead together to…

To address the challenges of sensor fusion and safety risk prediction, contemporary closed-loop autonomous driving neural networks leveraging imitation learning typically require a substantial volume of parameters and computational…

Recent research on automotive driving developed an efficient end-to-end learning mode that directly maps visual input to control commands. However, it models distinct driving variations in a single network, which increases learning…

Obstacle avoidance is a fundamental vision-based task essential for enabling quadrotors to perform advanced applications. When planning the trajectory, existing approaches both on optimization and learning typically regard quadrotor as a…

Safe and efficient autonomous driving maneuvers in an interactive and complex environment can be considerably challenging due to the unpredictable actions of other surrounding agents that may be cooperative or adversarial in their…