Robustness has been extensively studied in reinforcement learning (RL) t...
The prominence of embodied Artificial Intelligence (AI), which empowers
...
Recently, reward-conditioned reinforcement learning (RCRL) has gained
po...
Autonomous systems, such as self-driving vehicles, quadrupeds, and robot...
Active perception describes a broad class of techniques that couple plan...
A trustworthy reinforcement learning algorithm should be competent in so...
As a pivotal component to attaining generalizable solutions in human
int...
As shown by recent studies, machine intelligence-enabled systems are
vul...
Autonomous driving systems have witnessed a significant development duri...
Rare-event simulation techniques, such as importance sampling (IS),
cons...
Goal-directed generation, aiming for solving downstream tasks by generat...
Deep Generative Models (DGMs) are known for their superior capability in...
Safety is a critical concern when deploying reinforcement learning agent...
Existing neural network-based autonomous systems are shown to be vulnera...
Evaluating the reliability of intelligent physical systems against rare
...
Continuously learning to solve unseen tasks with limited experience has ...
Long-tail and rare event problems become crucial when autonomous driving...
The goal of acoustic (or sound) events detection (AED or SED) is to pred...
Naturalistic driving trajectories are crucial for the performance of
aut...
Attention mechanism has been widely applied to various sound-related tas...
Generating multi-vehicle trajectories analogous to these in real world c...
This paper proposes a navigation algorithm ori- ented to multi-agent dyn...
In this paper, we propose an enhanced triplet method that improves the
e...
In this paper, we present an accurate approach to estimate vehicles' pos...
This paper proposes an accurate approach to estimate vehicles' 3D pose a...