Related papers: SAIL: Scene-aware Adaptive Iterative Learning for …
Communication technologies enable coordination among connected and autonomous vehicles (CAVs). However, it remains unclear how to utilize shared information to improve the safety and efficiency of the CAV system in dynamic and complicated…
Distance-based reward mechanisms in deep reinforcement learning (DRL) navigation systems suffer from critical safety limitations in dynamic environments, frequently resulting in collisions when visibility is restricted. We propose DRL-NSUO,…
Autonomous off-road navigation requires robots to estimate terrain traversability from onboard sensors and plan motion accordingly. Conventional approaches typically rely on sampling-based planners such as MPPI to generate short-term…
Digital testing has emerged as a key paradigm for the development and verification of autonomous maritime navigation systems, yet the availability of realistic and diverse safety-critical encounter scenarios remains limited. Existing…
Contact-rich robotic manipulation requires representations that encode local geometry. Vision provides global context but lacks direct measurements of properties such as texture and hardness, whereas touch supplies these cues. Modern…
Real-world time series data often present recurrent or repetitive patterns and it is often generated in real time, such as transportation passenger volume, network traffic, system resource consumption, energy usage, and human gait.…
Autonomous Driving Systems (ADSs) are safety-critical, as real-world safety violations can result in significant losses. Rigorous testing is essential before deployment, with simulation testing playing a key role. However, ADSs are…
Autonomous driving is a complex task, which has been tackled since the first self-driving car ALVINN in 1989, with a supervised learning approach, or behavioral cloning (BC). In BC, a neural network is trained with state-action pairs that…
In our ever-evolving world, new data exhibits a long-tailed distribution, such as e-commerce platform reviews. This necessitates continuous model learning imbalanced data without forgetting, addressing the challenge of long-tailed…
Navigating urban intersections, especially when interacting with heterogeneous traffic participants, presents a formidable challenge for autonomous vehicles (AVs). In such environments, safety risks arise simultaneously from multiple…
In this paper, we consider the problem of long tail scenario modeling with budget limitation, i.e., insufficient human resources for model training stage and limited time and computing resources for model inference stage. This problem is…
Data in real-world object detection often exhibits the long-tailed distribution. Existing solutions tackle this problem by mitigating the competition between the head and tail categories. However, due to the scarcity of training samples,…
Reliable collision avoidance under extreme situations remains a critical challenge for autonomous vehicles. While large language models (LLMs) offer promising reasoning capabilities, their application in safety-critical evasive maneuvers is…
Anomaly detection (AD) aims to identify defective images and localize their defects (if any). Ideally, AD models should be able to detect defects over many image classes; without relying on hard-coded class names that can be uninformative…
Achieving fully autonomous driving systems requires learning rational decisions in a wide span of scenarios, including safety-critical and out-of-distribution ones. However, such cases are underrepresented in real-world corpus collected by…
Recent advances in high-fidelity simulators have enabled closed-loop training of autonomous driving agents, potentially solving the distribution shift in training v.s. deployment and allowing training to be scaled both safely and cheaply.…
Autonomous vehicles are suited for continuous area patrolling problems. Finding an optimal patrolling strategy can be challenging due to unknown environmental factors, such as wind or landscape; or autonomous vehicles' constraints, such as…
Ensuring both safety and efficiency in decision-making for autonomous driving systems remains a fundamental challenge. Traditional Deep Reinforcement Learning (DRL) suffers from unsafe random exploration and slow convergence, while Large…
Reliable prediction of train delays is essential for enhancing the robustness and efficiency of railway transportation systems. In this work, we reframe delay forecasting as a stochastic simulation task, modeling state-transition dynamics…
Self-imitation learning is a Reinforcement Learning (RL) method that encourages actions whose returns were higher than expected, which helps in hard exploration and sparse reward problems. It was shown to improve the performance of…