AIConfPaper
← Search

Lukas Schneider

8 accepted papers

2025

Monte-Carlo Tree Search with Uncertainty Propagation via Optimal Transport

Tuan Quang Dam, Pascal Stenger, Lukas Schneider, Joni Pajarinen, Carlo D'Eramo, Odalric-Ambrym Maillard
ICML 2025spotlight

This paper introduces a novel backup strategy for Monte-Carlo Tree Search (MCTS) tailored for highly stochastic and partially observable Markov decision processes. We adopt a probabilistic approach, modeling both value and action-value nodes as Gaussian distributions, to introduce a novel backup ope…

Cited by 3Source ↗PDF ↗Scholar ↗
2024

ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association

Shuxiao Ding, Lukas Schneider, Marius Cordts, Juergen Gall
CVPR 2024poster

Many query-based approaches for 3D Multi-Object Tracking (MOT) adopt the tracking-by-attention paradigm utilizing track queries for identity-consistent detection and object queries for identity-agnostic track spawning. Tracking-by-attention however entangles detection and tracking queries in one emb…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2024

DualAD: Disentangling the Dynamic and Static World for End-to-End Driving

Simon Doll, Niklas Hanselmann, Lukas Schneider, Richard Schulz, Marius Cordts, Markus Enzweiler +1
CVPR 2024poster

State-of-the-art approaches for autonomous driving integrate multiple sub-tasks of the overall driving task into a single pipeline that can be trained in an end-to-end fashion by passing latent representations between the different modules. In contrast to previous approaches that rely on a unified g…

Cited by 5Source ↗PDF ↗Scholar ↗
2024

Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning

Lukas Schneider, Jonas Frey, Takahiro Miki, Marco Hutter
ICRA 2024poster

Deployment in hazardous environments requires robots to understand the risks associated with their actions and movements to prevent accidents. Despite its importance, these risks are not explicitly modeled by currently deployed locomotion controllers for legged robots. In this work, we propose a ris…

Cited by 13Source ↗Scholar ↗
2024

S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking With Adaptive Spatio-Temporal Appearance Representations

Simon Doll, Niklas Hanselmann, Lukas Schneider, Richard Schulz, Markus Enzweiler, Hendrik P. A. Lensch
RA-L 2024

Following the tracking-by-attention paradigm, this letter introduces an object-centric, transformer-based framework for tracking in 3D. Traditional model-based tracking approaches incorporate the geometric effect of object- and ego motion between frames with a geometric motion model. Inspired by thi

Cited by 13Source ↗Scholar ↗
2023

3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking

Shuxiao Ding, Eike Rehder, Lukas Schneider, Marius Cordts, Juergen Gall
ICCV 2023poster

Tracking 3D objects accurately and consistently is crucial for autonomous vehicles, enabling more reliable downstream tasks such as trajectory prediction and motion planning. Based on the substantial progress in object detection in recent years, the tracking-by-detection paradigm has become a popula…

Cited by 35PDF ↗code ↗Scholar ↗
2022

SpatialDETR: Robust Scalable Transformer-Based 3D Object Detection from Multi-View Camera Images with Global Cross-Sensor Attention

Simon Doll, Richard Schulz, Lukas Schneider, Viviane Benzin, Markus Enzweiler, Hendrik P.A. Lensch
ECCV 2022poster

"Based on the key idea of DETR this paper introduces an object-centric 3D object detection framework that operates on a limited number of 3D object queries instead of dense bounding box proposals followed by non-maximum suppression. After image feature extraction a decoder-only transformer architect…

Cited by 30Source ↗PDF ↗code ↗Scholar ↗
2022

Structural Knowledge Distillation for Object Detection

Philip De Rijk, Lukas Schneider, Marius Cordts, Dariu Gavrila
NeurIPS 2022accept

Knowledge Distillation (KD) is a well-known training paradigm in deep neural networks where knowledge acquired by a large teacher model is transferred to a small student. KD has proven to be an effective technique to significantly improve the student's performance for various tasks including object…

Cited by 35Source ↗PDF ↗Scholar ↗