Accumulating substantial volumes of real-world driving data proves pivot...
Safe Reinforcement Learning (RL) aims to find a policy that achieves hig...
Point clouds are naturally sparse, while image pixels are dense. The
inc...
We present NeRF-Det, a novel method for indoor 3D detection with posed R...
In this note, we observe that quantum logspace computations are verifiab...
We present a model that can perform multiple vision tasks and can be ada...
We prove the first polynomial separation between randomized and determin...
Imitation Learning (IL) is a widely used framework for learning imitativ...
Hierarchical reinforcement learning (RL) can accelerate long-horizon
dec...
Self-training is an important technique for solving semi-supervised lear...
Autonomous racing control is a challenging research problem as vehicles ...
By identifying four important components of existing LiDAR-camera 3D obj...
Current LiDAR odometry, mapping and localization methods leverage point-...
Let ℒ be a language that can be decided in linear space and let
ϵ >0 be ...
Given the large-scale data and the high annotation cost,
pretraining-fin...
Traffic simulation plays a crucial role in evaluating and improving
auto...
In a work by Raz (J. ACM and FOCS 16), it was proved that any algorithm ...
Autonomous racing has become a popular sub-topic of autonomous driving i...
While recent camera-only 3D detection methods leverage multiple timestep...
Leveraging multi-modal fusion, especially between camera and LiDAR, has
...
Simulation has played an important role in efficiently evaluating
self-d...
Trajectory prediction is one of the essential tasks for autonomous vehic...
3D scene flow estimation from point clouds is a low-level 3D motion
perc...
With information from multiple input modalities, sensor fusion-based
alg...
Planning under social interactions with other agents is an essential pro...
Offline Reinforcement learning (RL) has shown potent in many safe-critic...
Deep learning has recently achieved significant progress in trajectory
f...
Conditional behavior prediction (CBP) builds up the foundation for a coh...
We prove that for every 3-player (3-prover) game 𝒢 with value less
than ...
Motion forecasting in highly interactive scenarios is a challenging prob...
While numerous 3D detection works leverage the complementary relationshi...
We prove that for every 3-player game with binary questions and answers ...
While autonomous vehicles still struggle to solve challenging situations...
Active learning aims to select the most informative samples to exploit
l...
Accurately predicting possible behaviors of traffic participants is an
e...
Multi-agent behavior modeling and trajectory forecasting are crucial for...
Reinforcement Learning (RL) has been shown effective in domains where th...
When autonomous vehicles still struggle to solve challenging situations
...
We propose an imitation learning system for autonomous driving in urban
...
Microscopic epidemic models are powerful tools for government policy mak...
Motion planning under uncertainty is of significant importance for
safet...
High definition (HD) maps have demonstrated their essential roles in ena...
We give a new proof of the fact that the parallel repetition of the
(3-p...
3D point-clouds and 2D images are different visual representations of th...
3D point-cloud-based perception is a challenging but crucial computer vi...
Detecting dynamic objects and predicting static road information such as...
Generating diverse and comprehensive interacting agents to evaluate the
...
Autonomous vehicles need to handle various traffic conditions and make s...
Autonomous vehicles (AVs) need to interact with other traffic participan...
The availability of many real-world driving datasets is a key reason beh...