相关论文: Exploring Imitation Learning for Autonomous Drivin…

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes…

Neural Memory Networks (NMNs) have received increased attention in recent years compared to deep architectures that use a constrained memory. Despite their new appeal, the success of NMNs hinges on the ability of the gradient-based…

Sampling-based trajectory planners are widely used for agile autonomous driving due to their ability to generate fast, smooth, and kinodynamically feasible trajectories. However, their behavior is often governed by a cost function with…

Recent work on domain-specific reasoning with large language models (LLMs) often relies on training-intensive approaches that require parameter updates. While activation steering has emerged as a parameter efficient alternative, existing…

Imitation learning often assumes that demonstrations are close to optimal according to some fixed, but unknown, cost function. However, according to satisficing theory, humans often choose acceptable behavior based on their personal (and…

Expert human drivers perform actions relying on traffic laws and their previous experience. While traffic laws are easily embedded into an artificial brain, modeling human complex behaviors which come from past experience is a more…

To construct effective teaming strategies between humans and AI systems in complex, risky situations requires an understanding of individual preferences and behaviors of humans. Previously this problem has been treated in case-specific or…

Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task. This issue arises due to the model's tendency to overwrite previously acquired knowledge with new…

Autonomous driving has attracted great attention from both academics and industries. To realise autonomous driving, Deep Imitation Learning (DIL) is treated as one of the most promising solutions, because it improves autonomous driving…

Diffusion models have demonstrated strong capabilities for modeling human-like driving behaviors in autonomous driving, but their iterative sampling process induces substantial latency, and operating directly on raw trajectory points forces…

Autonomous traffic control systems are large-scale systems with critical goals. Due to the dynamic nature of the surrounding world of these systems, assuring the satisfaction of their properties at runtime and in the presence of a change is…

This works presents a formulation for visual navigation that unifies map based spatial reasoning and path planning, with landmark based robust plan execution in noisy environments. Our proposed formulation is learned from data and is thus…

Augmented reality applications have rapidly spread across online platforms, allowing consumers to virtually try-on a variety of products, such as makeup, hair dying, or shoes. However, parametrizing a renderer to synthesize realistic images…

The technological and scientific challenges involved in the development of autonomous vehicles (AVs) are currently of primary interest for many automobile companies and research labs. However, human-controlled vehicles are likely to remain…

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…

Recently, deep reinforcement learning (DRL) methods have achieved impressive performance on tasks in a variety of domains. However, neural network policies produced with DRL methods are not human-interpretable and often have difficulty…

A major obstacle to developing artificial intelligence applications capable of true lifelong learning is that artificial neural networks quickly or catastrophically forget previously learned tasks when trained on a new one. Numerous methods…

We study the problem of target stabilization with robust obstacle avoidance in robots and vehicles that have access only to vision-based sensors for the purpose of realtime localization. This problem is particularly challenging due to the…

In imitation learning, an agent learns how to behave in an environment with an unknown cost function by mimicking expert demonstrations. Existing imitation learning algorithms typically involve solving a sequence of planning or…

Manipulation tasks often consist of subtasks, each representing a distinct skill. Mastering these skills is essential for robots, as it enhances their autonomy, efficiency, adaptability, and ability to work in their environment. Learning…