Author name cluster

Mark Campbell

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

ICRA Conference 2025 Conference Paper

Semantic and Feature Guided Uncertainty Quantification of Visual Localization for Autonomous Vehicles

Qiyuan Wu
Mark Campbell

The uncertainty quantification of sensor measurements coupled with deep learning networks is crucial for many robotics systems, especially for safety-critical applications such as self-driving cars. This paper develops an uncertainty quantification approach in the context of visual localization for autonomous driving, where locations are selected based on images. Key to our approach is to learn the measurement uncertainty using light-weight sensor error model, which maps both image feature and semantic information to 2-dimensional error distribution. Our approach enables uncertainty estimation conditioned on the specific context of the matched image pair, implicitly capturing other critical, unannotated factors (e. g. , city vs. highway, dynamic vs. static scenes, winter vs. summer) in a latent manner. We demonstrate the accuracy of our uncertainty prediction framework using the Ithaca365 dataset, which includes variations in lighting and weather (sunny, night, snowy). Both the uncertainty quantification of the sensor+network is evaluated, along with Bayesian localization filters using unique sensor gating method. Results show that the measurement error does not follow a Gaussian distribution with poor weather and lighting conditions, and is better predicted by our Gaussian Mixture model.

Details

NeurIPS Conference 2024 Conference Paper

DiffuBox: Refining 3D Object Detection with Point Diffusion

Xiangyu Chen
Zhenzhen Liu
Katie Z. Luo
Siddhartha Datta
Adhitya Polavaram
Yan Wang
Yurong You
Boyi Li

Ensuring robust 3D object detection and localization is crucial for many applications in robotics and autonomous driving. Recent models, however, face difficulties in maintaining high performance when applied to domains with differing sensor setups or geographic locations, often resulting in poor localization accuracy due to domain shift. To overcome this challenge, we introduce a novel diffusion-based box refinement approach. This method employs a domain-agnostic diffusion model, conditioned on the LiDAR points surrounding a coarse bounding box, to simultaneously refine the box's location, size, and orientation. We evaluate this approach under various domain adaptation settings, and our results reveal significant improvements across different datasets, object classes and detectors. Our PyTorch implementation is available at https: //github. com/cxy1997/DiffuBox.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery

Katie Luo
Zhenzhen Liu
Xiangyu Chen
Yurong You
Sagie Benaim
Cheng Perng Phoo
Mark Campbell
Wen Sun

Recent advances in machine learning have shown that Reinforcement Learning from Human Feedback (RLHF) can improve machine learning models and align them with human preferences. Although very successful for Large Language Models (LLMs), these advancements have not had a comparable impact in research for autonomous vehicles—where alignment with human expectations can be imperative. In this paper, we propose to adapt similar RL-based methods to unsupervised object discovery, i. e. learning to detect objects from LiDAR points without any training labels. Instead of labels, we use simple heuristics to mimic human feedback. More explicitly, we combine multiple heuristics into a simple reward function that positively correlates its score with bounding box accuracy, i. e. , boxes containing objects are scored higher than those without. We start from the detector’s own predictions to explore the space and reinforce boxes with high rewards through gradient updates. Empirically, we demonstrate that our approach is not only more accurate, but also orders of magnitudes faster to train compared to prior works on object discovery. Code is available at https: //github. com/katieluo88/DRIFT.

PDF Details

NeurIPS Conference 2022 Conference Paper

Unsupervised Adaptation from Repeated Traversals for Autonomous Driving

Yurong You
Cheng Perng Phoo
Katie Luo
Travis Zhang
Wei-Lun Chao
Bharath Hariharan
Mark Campbell
Kilian Q. Weinberger

For a self-driving car to operate reliably, its perceptual system must generalize to the end-user's environment --- ideally without additional annotation efforts. One potential solution is to leverage unlabeled data (e. g. , unlabeled LiDAR point clouds) collected from the end-users' environments (i. e. target domain) to adapt the system to the difference between training and testing environments. While extensive research has been done on such an unsupervised domain adaptation problem, one fundamental problem lingers: there is no reliable signal in the target domain to supervise the adaptation process. To overcome this issue we observe that it is easy to collect unsupervised data from multiple traversals of repeated routes. While different from conventional unsupervised domain adaptation, this assumption is extremely realistic since many drivers share the same roads. We show that this simple additional assumption is sufficient to obtain a potent signal that allows us to perform iterative self-training of 3D object detectors on the target domain. Concretely, we generate pseudo-labels with the out-of-domain detector but reduce false positives by removing detections of supposedly mobile objects that are persistent across traversals. Further, we reduce false negatives by encouraging predictions in regions that are not persistent. We experiment with our approach on two large-scale driving datasets and show remarkable improvement in 3D object detection of cars, pedestrians, and cyclists, bringing us a step closer to generalizable autonomous driving.

PDF Details

JAIR Journal 2020 Journal Article

Planning High-Level Paths in Hostile, Dynamic, and Uncertain Environments

Jacopo Banfi
Vikram Shree
Mark Campbell

This paper introduces and studies a graph-based variant of the path planning problem arising in hostile environments. We consider a setting where an agent (e.g. a robot) must reach a given destination while avoiding being intercepted by probabilistic entities which exist in the graph with a given probability and move according to a probabilistic motion pattern known a priori. Given a goal vertex and a deadline to reach it, the agent must compute the path to the goal that maximizes its chances of survival. We study the computational complexity of the problem, and present two algorithms for computing high quality solutions in the general case: an exact algorithm based on Mixed-Integer Nonlinear Programming, working well in instances of moderate size, and a pseudo-polynomial time heuristic algorithm allowing to solve large scale problems in reasonable time. We also consider the two limit cases where the agent can survive with probability 0 or 1, and provide specialized algorithms to detect these kinds of situations more efficiently.

PDF Details DOI

NeurIPS Conference 2020 Conference Paper

Wasserstein Distances for Stereo Disparity Estimation

Divyansh Garg
Yan Wang
Bharath Hariharan
Mark Campbell
Kilian Q. Weinberger
Wei-Lun Chao

Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. This leads to inaccurate results when the true depth or disparity does not match any of these values. The fact that this distribution is usually learned indirectly through a regression loss causes further problems in ambiguous regions around object boundaries. We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values, and a new loss function that is derived from the Wasserstein distance between the true and the predicted distributions. We validate our approach on a variety of tasks, including stereo disparity and depth estimation, and the downstream 3D object detection. Our approach drastically reduces the error in ambiguous regions, especially around object boundaries that greatly affect the localization of objects in 3D, achieving the state-of-the-art in 3D object detection for autonomous driving.

PDF Details

AAMAS Conference 2019 Conference Paper

High-Level Path Planning in Hostile Dynamic Environments

Jacopo Banfi
Mark Campbell

In this paper, we introduce and study a graph-based variant of the path planning problem arising in hostile environments. Here, the robot must reach a given destination while avoiding being intercepted by probabilistic entities which exist in the graph with a given probability and move according to a probabilistic motion pattern. Given a deadline to reach its goal, the robot must compute a path that maximizes its chances of survival. To solve this problem, which is proven to be NP-hard, we present a convex Mixed-Integer Nonlinear Program to compute optimal solutions and a more scalable heuristic algorithm.

PDF

AIJ Journal 2003 Journal Article

Multiple agent-based autonomy for satellite constellations

Thomas Schetter
Mark Campbell
Derek Surka

Multiple, highly autonomous, satellite systems are envisioned in the near future because they are capable of higher performance, lower cost, better fault tolerance, reconfigurability and upgradability. This paper presents an architecture and multi-agent design and simulation environment that will enable agent-based multi-satellite systems to fulfill their complex mission objectives, termed ObjectAgentTM. Its application is shown for a distributed aperture radar mission, although its applicability spans many types of missions. Required spacecraft functions, software agents, and multi-agent organisations are described for the radar mission, as well as their implementation. Agent-based simulations of mission case studies show the autonomous operation of the multi-agent architecture, which can then be used to build, evaluate and compare autonomous software architectures for multiple satellite systems.

Details DOI