Related papers: Dynamic Interaction-Aware Scene Understanding for …
This paper investigates a fundamental problem of scene understanding: how to parse a scene image into a structured configuration (i.e., a semantic object hierarchy with object interaction relations). We propose a deep architecture…
State-of-the-art reinforcement learning algorithms predominantly learn a policy from either a numerical state vector or images. Both approaches generally do not take structural knowledge of the task into account, which is especially…
We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. Using…
Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model. Here we introduce a new…
Ensuring validation for highly automated driving poses significant obstacles to the widespread adoption of highly automated vehicles. Scenario-based testing offers a potential solution by reducing the homologation effort required for these…
Reasoning about objects, relations, and physics is central to human intelligence, and a key goal of artificial intelligence. Here we introduce the interaction network, a model which can reason about how objects in complex systems interact,…
Learning robot navigation strategies among pedestrian is crucial for domain based applications. Combining perception, planning and prediction allows us to model the interactions between robots and pedestrians, resulting in impressive…
Merging into dense highway traffic for an autonomous vehicle is a complex decision-making task, wherein the vehicle must identify a potential gap and coordinate with surrounding human drivers, each of whom may exhibit diverse driving…
Behavioral and semantic relationships play a vital role on intelligent self-driving vehicles and ADAS systems. Different from other research focused on trajectory, position, and bounding boxes, relationship data provides a human…
Synthesizing free-view photo-realistic images is an important task in multimedia. With the development of advanced driver assistance systems~(ADAS) and their applications in autonomous vehicles, experimenting with different scenarios…
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group…
RGB-D has gradually become a crucial data source for understanding complex scenes in assisted driving. However, existing studies have paid insufficient attention to the intrinsic spatial properties of depth maps. This oversight…
Active traffic management with autonomous vehicles offers the potential for reduced congestion and improved traffic flow. However, developing effective algorithms for real-world scenarios requires overcoming challenges related to…
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…
Autonomous vehicle path planning has reached a stage where safety and regulatory compliance are crucial. This paper presents an approach that integrates a motion planner with a deep reinforcement learning model to predict potential traffic…
Traffic signal control is an emerging application scenario for reinforcement learning. Besides being as an important problem that affects people's daily life in commuting, traffic signal control poses its unique challenges for reinforcement…
Adaptive traffic signal control, which adjusts traffic signal timing according to real-time traffic, has been shown to be an effective method to reduce traffic congestion. Available works on adaptive traffic signal control make responsive…
In this work, we aim to predict the future motion of vehicles in a traffic scene by explicitly modeling their pairwise interactions. Specifically, we propose a graph neural network that jointly predicts the discrete interaction modes and…
Long-term complex activity recognition and localisation can be crucial for decision making in autonomous systems such as smart cars and surgical robots. Here we address the problem via a novel deformable, spatiotemporal scene graph…
There are two main algorithmic approaches to autonomous driving systems: (1) An end-to-end system in which a single deep neural network learns to map sensory input directly into appropriate warning and driving responses. (2) A mediated…