About

Mark Campbell joined the faculty of the Sibley School of Mechanical and Aerospace Engineering at Cornell University in 2001 and holds the position of John A. Mellowes ’60 Professor of Mechanical and Aerospace Engineering. His research broadly impacts aerospace and robotic systems, focusing on control and autonomy for robotics, aircraft, and spacecraft. His areas of expertise include machine learning, perception and sensor fusion, optimization and learning-based control and planning, decentralized and distributed estimation and control across teams, and human-robotic interaction. Campbell's work encompasses control of flexible structures, formation flying spacecraft, student-designed satellites, cooperative UAVs, self-driving cars, and human-robotic teaming.

Research topics

• Computer Science
• Artificial Intelligence
• Geography
• Remote sensing
• Computer vision

Selected publications

• Real-time Estimator of Actuator Control and Health (REACH) on an Eel-Inspired Soft Robot

  2025-04-22

  articleSenior author

  An actuator health estimation algorithm for a soft swimming robot that can perform anguilliform swimming is developed. Due to harsh operational environments of underwater robots, and the common degradation of soft robot materials and actuators, accurate estimation of actuator functionality is necessary for robots to perform their missions as well as return to base in the event of actuator degradation and failure. Termed REACH (Real-time Estimator of Actuator Control and Health), the architecture employs a soft robot model, sigma point filter, and a formal statistical hypothesis test to adequately capture the nonlinearities and changes over time. The performance of REACH using three sensor types (GPS, IMU, and Bend Sensor) with one sensor on each actuator is compared, demonstrating that both bend sensor and IMU are adequate choices. Sensor quantity and placement are evaluated for IMU and bend sensor, showing two sensors are sufficient for IMU, whereas three sensors are needed for bend sensor. Three swimming gaits (linear swimming, wide turning, tight turning) are compared, demonstrating that REACH can successfully predict actuator health for all three gaits, with minimal differences in performance. A filter validation method shows the fault estimation algorithm is statistically consistent in finding the correct degradation. The approach is experimentally evaluated using bend sensor data collected from a fish robot, demonstrating that REACH can successfully estimate actuator health with noisy data and variations in manufacturing.

  PublisherDOI

• Transfer Your Perspective: Controllable 3D Generation from Any Viewpoint in a Driving Scene

  ArXiv.org · 2025-02-10

  preprintOpen access

  Self-driving cars relying solely on ego-centric perception face limitations in sensing, often failing to detect occluded, faraway objects. Collaborative autonomous driving (CAV) seems like a promising direction, but collecting data for development is non-trivial. It requires placing multiple sensor-equipped agents in a real-world driving scene, simultaneously! As such, existing datasets are limited in locations and agents. We introduce a novel surrogate to the rescue, which is to generate realistic perception from different viewpoints in a driving scene, conditioned on a real-world sample - the ego-car's sensory data. This surrogate has huge potential: it could potentially turn any ego-car dataset into a collaborative driving one to scale up the development of CAV. We present the very first solution, using a combination of simulated collaborative data and real ego-car data. Our method, Transfer Your Perspective (TYP), learns a conditioned diffusion model whose output samples are not only realistic but also consistent in both semantics and layouts with the given ego-car data. Empirical results demonstrate TYP's effectiveness in aiding in a CAV setting. In particular, TYP enables us to (pre-)train collaborative perception algorithms like early and late fusion with little or no real-world collaborative data, greatly facilitating downstream CAV applications.

  PublisherOA PDFDOI

• Mixed Signals: A Diverse Point Cloud Dataset for Heterogeneous LiDAR V2X Collaboration

  2025-10-19

  preprintOpen access

  Vehicle-to-everything (V2X) collaborative perception has emerged as a promising solution to address the limitations of single-vehicle perception systems. However, existing V2X datasets are limited in scope, diversity, and quality. To address these gaps, we present Mixed Signals, a comprehensive V2X dataset featuring 45.1k point clouds and 240.6k bounding boxes collected from three connected autonomous vehicles (CAVs) equipped with two different configurations of LiDAR sensors, plus a roadside unit with dual LiDARs. Our dataset provides point clouds and bounding box annotations across 10 classes, ensuring reliable data for perception training. We provide detailed statistical analysis on the quality of our dataset and extensively benchmark existing V2X methods on it. The Mixed Signals dataset is ready-to-use, with precise alignment and consistent annotations across time and viewpoints. Dataset website is available at https://mixedsignalsdataset.cs.cornell.edu/.

  PublisherOA PDFDOI

• Drawing to Conclusions: Sketching the Modulated Subject of Le Corbusier

  Interstices Journal of Architecture and Related Arts · 2024-06-11

  articleOpen access1st authorCorresponding

  ***

  PublisherOA PDFDOI

• Better Monocular 3D Detectors with LiDAR from the Past

  2024-05-13 · 3 citations

  article

  Accurate 3D object detection is crucial to autonomous driving. Though LiDAR-based detectors have achieved impressive performance, the high cost of LiDAR sensors precludes their widespread adoption in affordable vehicles. Camera-based detectors are cheaper alternatives but often suffer inferior performance compared to their LiDAR-based counterparts due to inherent depth ambiguities in images. In this work, we seek to improve monocular 3D detectors by leveraging unlabeled historical LiDAR data. Specifically, at inference time, we assume that the camera-based detectors have access to multiple unlabeled LiDAR scans from past traversals at locations of interest (potentially from other high-end vehicles equipped with LiDAR sensors). Under this setup, we proposed a novel, simple, and end-to-end trainable framework, termed AsyncDepth, to effectively extract relevant features from asynchronous LiDAR traversals of the same location for monocular 3D detectors. We show consistent and significant performance gain (up to 9 AP) across multiple state-of-the-art models and datasets with a negligible additional latency of 9.66 ms and a small storage cost. Our code can be found at https://github.com/YurongYou/AsyncDepth.

  PublisherDOI

• Learning 3D Perception from Others' Predictions

  arXiv (Cornell University) · 2024-10-03

  preprintOpen access

  Accurate 3D object detection in real-world environments requires a huge amount of annotated data with high quality. Acquiring such data is tedious and expensive, and often needs repeated effort when a new sensor is adopted or when the detector is deployed in a new environment. We investigate a new scenario to construct 3D object detectors: learning from the predictions of a nearby unit that is equipped with an accurate detector. For example, when a self-driving car enters a new area, it may learn from other traffic participants whose detectors have been optimized for that area. This setting is label-efficient, sensor-agnostic, and communication-efficient: nearby units only need to share the predictions with the ego agent (e.g., car). Naively using the received predictions as ground-truths to train the detector for the ego car, however, leads to inferior performance. We systematically study the problem and identify viewpoint mismatches and mislocalization (due to synchronization and GPS errors) as the main causes, which unavoidably result in false positives, false negatives, and inaccurate pseudo labels. We propose a distance-based curriculum, first learning from closer units with similar viewpoints and subsequently improving the quality of other units' predictions via self-training. We further demonstrate that an effective pseudo label refinement module can be trained with a handful of annotated data, largely reducing the data quantity necessary to train an object detector. We validate our approach on the recently released real-world collaborative driving dataset, using reference cars' predictions as pseudo labels for the ego car. Extensive experiments including several scenarios (e.g., different sensors, detectors, and domains) demonstrate the effectiveness of our approach toward label-efficient learning of 3D perception from other units' predictions.

  PublisherOA PDFDOI

• Near Real-Time Wildfire Damage Assessment using Aerial Thermal Imagery and Machine Learning

  2024-12-15 · 1 citations

  article

  This project aims at developing an AI system to provide a reliable assessment of the structural damage caused by wildfires in the first burn period. Our approach uses multimodal data, including multispectral aerial images, historical post-fire damage assessment data, and building footprints, to create an association between damage data and structure footprints. We use these associations to generate features and use machine learning methods to assess the level of damage to structures. The resulting AI-driven system can be used to provide wildfire-induced structural damage assessments in near-real-time using only aerial images for future fires. We provide damage assessment results on several megafires in California to demonstrate the applicability of our approach to real wildfire scenarios.

  PublisherDOI

• Better Monocular 3D Detectors with LiDAR from the Past

  arXiv (Cornell University) · 2024-04-08

  preprintOpen access

  Accurate 3D object detection is crucial to autonomous driving. Though LiDAR-based detectors have achieved impressive performance, the high cost of LiDAR sensors precludes their widespread adoption in affordable vehicles. Camera-based detectors are cheaper alternatives but often suffer inferior performance compared to their LiDAR-based counterparts due to inherent depth ambiguities in images. In this work, we seek to improve monocular 3D detectors by leveraging unlabeled historical LiDAR data. Specifically, at inference time, we assume that the camera-based detectors have access to multiple unlabeled LiDAR scans from past traversals at locations of interest (potentially from other high-end vehicles equipped with LiDAR sensors). Under this setup, we proposed a novel, simple, and end-to-end trainable framework, termed AsyncDepth, to effectively extract relevant features from asynchronous LiDAR traversals of the same location for monocular 3D detectors. We show consistent and significant performance gain (up to 9 AP) across multiple state-of-the-art models and datasets with a negligible additional latency of 9.66 ms and a small storage cost.

  PublisherOA PDFDOI

• Modeling and Control of an Eel-Inspired Soft Robot for Design Optimization

  2024-08-28 · 2 citations

  articleSenior author

  Anguilliform locomotion is a highly efficient swimming mode; the advent of new materials for soft robots enables the development of an eel-inspired soft robot. This paper presents a simulation model of an eel-inspired soft robot designed for anguilliform swimming. This model can aid in design optimization and the development of model-based estimation, reasoning, and control systems. A Finite Element Method (FEM) model of an elastic rod is used to capture the soft materials of the robotic fish, which makes it particularly amenable to variation over time as the material properties change. The material model is coupled with a hydrodynamic force model to simulate the behavior of a soft, elongated robot in water. The model is used to demonstrate the effectiveness of the proposed control approaches in achieving desired swimming behaviors. It also provides insights into design decisions, including the robustness of different system configurations and the impact of material degradation and failure. The results show that slightly asymmetric designs are advantageous, offering comparable swimming velocities but greater maneuverability. This model can be used to guide future robotic design decisions aimed at optimizing performance for specific tasks.

  PublisherDOI

• SWIFT: Strategic Weather-informed Image-based Forecasting for Trajectories

  2024-10-14

  articleSenior author

  Predicting agents’ trajectories in complex environments is critical for achieving safe autonomous robot navigation. Empirically, agents’ decisions and preferences are susceptible to changes in environmental factors (e.g., interactions with other agents, weather conditions, traffic rules). State-of-the-art methods rely on High-Definition (HD) or semantic maps to model the environment, but do not take into account unpredictable factors such as complex weather conditions. In addition, since HD maps are nontrivial to obtain, those methods are limited in the scope of environments they can be applied in. We propose a more flexible graph based trajectory prediction model that uses only images to model the environment, without requiring expensive map information. We experimentally validate our proposed model, demonstrating robust performances in trajectory prediction compared to state-of-the-art methods, and outperform in complex environments that cannot be modeled with purely map based methods, such as diverse weather conditions.

  PublisherDOI

Recent grants

• NRI: FND: Probabilistic Hypothesis-Driven Adaptive Human-Robot Teams

  NSF · $664k · 2018–2023

• EHS: Hybrid Estimation and Control with Bounded Probabilities

  NSF · $270k · 2004–2007

• S&AS: INT: Inference, Reasoning, and Learning for Robust Autonomous Driving

  NSF · $1.4M · 2017–2023

• NRI: Collaborative Research: Modeling and Verification of Language-based Interaction

  NSF · $700k · 2014–2019

• CPS:Medium: Tightly Integrated Perception and Planning in Intelligent Robotics

  NSF · $1.5M · 2009–2013

Frequent coauthors

• Giuseppe C. Calafiore

  Polytechnic University of Turin

  65 shared

• Karen Rudie

  Queen's University

  64 shared

• Wei‐Lun Chao

  40 shared

• Kilian Q. Weinberger

  36 shared

• Bharath Hariharan

  32 shared

• Nisar Ahmed

  29 shared

• Daniel E. Clark

  University of Southampton

  25 shared

• Yurong You

  23 shared

Awards & honors

• U.S. Air Force Chief of Staff Award for Exceptional Public S…
• Cornell Stephen H. Weiss Presidential Fellow Award
• Ralph S. Watts `72 Award
• Douglas Whitney Award
• Stephen Miles `57 Award