• Corpus ID: 243847631

Towards Learning Generalizable Driving Policies from Restricted Latent Representations

  title={Towards Learning Generalizable Driving Policies from Restricted Latent Representations},
  author={Behrad Toghi and Rodolfo Valiente and Ramtin Pedarsani and Yaser P. Fallah},
—Training intelligent agents that can drive au- tonomously in various urban and highway scenarios has been a hot topic in the robotics society within the last decades. However, the diversity of driving environments in terms of road topology and positioning of the neighboring vehicles makes this problem very challenging. It goes without saying that although scenario-specific driving policies for autonomous driving are promising and can improve transportation safety and efficiency, they are not a… 
2 Citations

Exploring the trade off between human driving imitation and safety for traffic simulation

It is shown that a trade-off exists between imitating human driving and maintaining safety when learning driving policies and a multi objective learning algorithm (MOPPO) is proposed that improves both objectives together.

Robustness and Adaptability of Reinforcement Learning-Based Cooperative Autonomous Driving in Mixed-Autonomy Traffic

The mixed-autonomy problem is formulated as a multi-agent reinforcement learning (MARL) problem and a decentralized framework and reward function for training cooperative AVs is proposed and enables AVs to learn the decision-making of HVs implicitly from experience and optimizes for a social utility while prioritizing safety and allowing adaptability.



LILA: Language-Informed Latent Actions

Language-Informed Latent Actions models are shown to be not only more sample efficient and performant than imitation learning and end-effector control baselines, but that they are also qualitatively preferred by users.

Altruistic Maneuver Planning for Cooperative Autonomous Vehicles Using Multi-agent Advantage Actor-Critic

A multi-agent variant of the synchronous Advantage Actor-Critic (A2C) algorithm is introduced and agents that coordinate with each other and can affect the behavior of human drivers to improve traffic flow and safety.

Learning latent actions to control assistive robots

This work finds that intuitive, user-friendly control of assistive robots can be achieved by embedding the robot’s high-dimensional actions into low-dimensional and human-controllable latent actions .

Cooperative Autonomous Vehicles that Sympathize with Human Drivers

A significant improvement in both safety and traffic-level metrics are demonstrated and it is concluded that the level of altruism in agents requires proper tuning as agents that are too altruistic also lead to sub-optimal traffic flow.

Social Coordination and Altruism in Autonomous Driving

A quantitative representation of the AVs’ social preferences and design a distributed reward structure that induces altruism into their decision-making process are introduced and Altruistic AVs are able to form alliances, guide the traffic, and affect the behavior of the HVs to handle competitive driving scenarios.

Learning Visually Guided Latent Actions for Assistive Teleoperation

This work develops assistive robots that condition their latent embeddings on visual inputs and indicates that structured visual representations improve few-shot performance and are subjectively preferred by users.

Learning Latent Representations to Influence Multi-Agent Interaction

This work proposes a reinforcement learning-based framework for learning latent representations of an agent's policy, where the ego agent identifies the relationship between its behavior and the other agent's future strategy and leverages these latent dynamics to influence the otherAgent, purposely guiding them towards policies suitable for co-adaptation.

Reinforcement Learning for Autonomous Driving with Latent State Inference and Spatial-Temporal Relationships

This work encodes prior knowledge on the latent states of other drivers through a framework that combines the reinforcement learner with a supervised learner and model the influence passing between different vehicles through graph neural networks (GNNs).

Performance Analysis of Cellular-V2X with Adaptive & Selective Power Control

This study reveals that while power control does not improve packet delivery performance of basic safety messages, it is beneficial to high priority event message delivery, and investigates the reasons for this behavior using simulations and analysis.

On the Road With 16 Neurons: Towards Interpretable and Manipulable Latent Representations for Visual Predictions in Driving Scenarios

A strategy for visual perception in the context of autonomous driving is proposed that uses compact representations that use as few as 16 neural units for each of the two basic driving concepts the authors consider: cars and lanes.