Mark W. Mueller
YOU?
Author Swipe
View article: A Tactile Feedback Approach to Path Recovery After High-Speed Impacts for Collision-Resilient Drones
A Tactile Feedback Approach to Path Recovery After High-Speed Impacts for Collision-Resilient Drones Open
Aerial robots are a well-established solution for exploration, monitoring, and inspection, thanks to their superior maneuverability and agility. However, in many environments, they risk crashing and sustaining damage after collisions. Trad…
View article: A Simulation Evaluation Suite for Robust Adaptive Quadcopter Control
A Simulation Evaluation Suite for Robust Adaptive Quadcopter Control Open
Robust adaptive control methods are essential for maintaining quadcopter performance under external disturbances and model uncertainties. However, fragmented evaluations across tasks, simulators, and implementations hinder systematic compa…
View article: Combining Large Language Models and Gradient-Free Optimization for Automatic Control Policy Synthesis
Combining Large Language Models and Gradient-Free Optimization for Automatic Control Policy Synthesis Open
Large Language models (LLMs) have shown promise as generators of symbolic control policies, producing interpretable program-like representations through iterative search. However, these models are not capable of separating the functional s…
View article: Autonomous Close-Proximity Photovoltaic Panel Coating Using a Quadcopter
Autonomous Close-Proximity Photovoltaic Panel Coating Using a Quadcopter Open
Photovoltaic (PV) panels are becoming increasingly widespread in the domain of renewable energy, and thus, small efficiency gains can have massive effects. Anti-reflective and self-cleaning coatings enhance panel performance but degrade ov…
View article: Untethered subcentimeter flying robots
Untethered subcentimeter flying robots Open
The miniaturization of insect-scale flying robots with untethered flights is extremely challenging as the tradeoff between mass and power becomes problematic. Here, a subcentimeter rotating-wing robot of 21 mg in weight and 9.4 mm in wings…
View article: PairTilt: Design and Control of an Active Tilt‐Rotor Quadcopter for Improved Efficiency and Agility
PairTilt: Design and Control of an Active Tilt‐Rotor Quadcopter for Improved Efficiency and Agility Open
This article presents PairTilt, a novel quadcopter design with two pairs of tiltable rotors, offering a balance between the simplicity of conventional quadcopters and the agility of complex tilt‐rotor systems. Despite being underactuated, …
View article: AgriNav: UAV Simulator for Vision-based Navigation in Agricultural Environments
AgriNav: UAV Simulator for Vision-based Navigation in Agricultural Environments Open
View article: A Tactile Feedback Approach to Path Recovery after High-Speed Impacts for Collision-Resilient Drones
A Tactile Feedback Approach to Path Recovery after High-Speed Impacts for Collision-Resilient Drones Open
Aerial robots are a well-established solution for exploration, monitoring, and inspection, thanks to their superior maneuverability and agility. However, in many environments, they risk crashing and sustaining damage after collisions. Trad…
View article: Synthesizing Interpretable Control Policies through Large Language Model Guided Search
Synthesizing Interpretable Control Policies through Large Language Model Guided Search Open
The combination of Large Language Models (LLMs), systematic evaluation, and evolutionary algorithms has enabled breakthroughs in combinatorial optimization and scientific discovery. We propose to extend this powerful combination to the con…
View article: Towards Safe and Efficient Through-the-Canopy Autonomous Fruit Counting with UAVs
Towards Safe and Efficient Through-the-Canopy Autonomous Fruit Counting with UAVs Open
We present an autonomous aerial system for safe and efficient through-the-canopy fruit counting. Aerial robot applications in large-scale orchards face significant challenges due to the complexity of fine-tuning flight paths based on orcha…
View article: ProxFly: Robust Control for Close Proximity Quadcopter Flight via Residual Reinforcement Learning
ProxFly: Robust Control for Close Proximity Quadcopter Flight via Residual Reinforcement Learning Open
This paper proposes the ProxFly, a residual deep Reinforcement Learning (RL)-based controller for close proximity quadcopter flight. Specifically, we design a residual module on top of a cascaded controller (denoted as basic controller) to…
View article: A Learning-based Quadcopter Controller with Extreme Adaptation
A Learning-based Quadcopter Controller with Extreme Adaptation Open
This paper introduces a learning-based low-level controller for quadcopters, which adaptively controls quadcopters with significant variations in mass, size, and actuator capabilities. Our approach leverages a combination of imitation lear…
View article: Team CERBERUS Wins the DARPA Subterranean Challenge: Technical Overview and Lessons Learned
Team CERBERUS Wins the DARPA Subterranean Challenge: Technical Overview and Lessons Learned Open
This article presents the CERBERUS robotic system-of-systems, which won the DARPA Subterranean Challenge Final Event in 2021. The Subterranean Challenge was organized by DARPA with the vision to facilitate the novel technologies necessary …
View article: Agri-fly: Simulator for Uncrewed Aerial Vehicle Flight in Agricultural Environments
Agri-fly: Simulator for Uncrewed Aerial Vehicle Flight in Agricultural Environments Open
We present Agri-fly, a simulator for Uncrewed Aerial Vehicles (UAVs) with a focus on agricultural applications. In addition to general flight simulator features, such as dynamics modeling and sensor synthesis, Agri-fly comes with an autono…
View article: Automated Layout and Control Co-Design of Robust Multi-UAV Transportation Systems
Automated Layout and Control Co-Design of Robust Multi-UAV Transportation Systems Open
The joint optimization of physical parameters and controllers in robotic systems is challenging. This is due to the difficulties of predicting the effect that changes in physical parameters have on final performances. At the same time, phy…
View article: One byte at a time: gathering best practices, guidelines, and resources for data standards to support ocean exploration and characterization
One byte at a time: gathering best practices, guidelines, and resources for data standards to support ocean exploration and characterization Open
Initiated through Presidential direction and now codified, the National Ocean Mapping, Exploration, and Characterization (NOMEC) Council comprises leaders from U.S. federal agencies with a shared goal of mapping all waters of the United St…
View article: Corrigendum: QUaRTM: A Quadcopter with Unactuated Rotor Tilting Mechanism capable of faster, more agile, and more efficient flight
Corrigendum: QUaRTM: A Quadcopter with Unactuated Rotor Tilting Mechanism capable of faster, more agile, and more efficient flight Open
[This corrects the article DOI: 10.3389/frobt.2022.1033715.].
View article: Evolving Flying Machines in Minecraft Using Quality Diversity
Evolving Flying Machines in Minecraft Using Quality Diversity Open
Minecraft is a great testbed for human creativity that has inspired the design of various structures and even functioning machines, including flying machines. EvoCraft is an API for programmatically generating structures in Minecraft, but …
View article: Design and control of a collision-resilient aerial vehicle with an icosahedron tensegrity structure
Design and control of a collision-resilient aerial vehicle with an icosahedron tensegrity structure Open
We introduce collision-resilient aerial vehicles with icosahedron tensegrity structures, capable of surviving high-speed impacts and resuming operations post-collision. We present a model-based design approach, which guides the selection o…
View article: QUaRTM: A Quadcopter with Unactuated Rotor Tilting Mechanism capable of faster, more agile, and more efficient flight
QUaRTM: A Quadcopter with Unactuated Rotor Tilting Mechanism capable of faster, more agile, and more efficient flight Open
We present QUaRTM – a novel quadcopter design capable of tilting the propellers into the forward flight direction, which reduces the drag area and therefore allows for faster, more agile, and more efficient flight. The vehicle can morph be…
View article: Learning a Single Near-hover Position Controller for Vastly Different Quadcopters
Learning a Single Near-hover Position Controller for Vastly Different Quadcopters Open
This paper proposes an adaptive near-hover position controller for quadcopters, which can be deployed to quadcopters of very different mass, size and motor constants, and also shows rapid adaptation to unknown disturbances during runtime. …
View article: Design and Control of a Midair-Reconfigurable Quadcopter Using Unactuated Hinges
Design and Control of a Midair-Reconfigurable Quadcopter Using Unactuated Hinges Open
In this article, a novel quadcopter capable of changing shape midflight is presented, allowing for operation in four configurations with the capability of sustained hover in three. This is accomplished without requiring actuators beyond th…
View article: Perception-aware receding horizon trajectory planning for multicopters with visual-inertial odometry
Perception-aware receding horizon trajectory planning for multicopters with visual-inertial odometry Open
Visual inertial odometry (VIO) is widely used for the state estimation of multicopters, but it may function poorly in environments with few visual features or in overly aggressive flights. In this work, we propose a perception-aware collis…
View article: Tethered Power for a Series of Quadcopters: Analysis and Applications
Tethered Power for a Series of Quadcopters: Analysis and Applications Open
Tethered quadcopters are used for extended flight operations where the power to the system is provided via a tether connected to an external power source. In this work, we consider a system of multiple quadcopters powered by a single tethe…
View article: Learning Torque Control for Quadrupedal Locomotion
Learning Torque Control for Quadrupedal Locomotion Open
Reinforcement learning (RL) has become a promising approach to developing controllers for quadrupedal robots. Conventionally, an RL design for locomotion follows a position-based paradigm, wherein an RL policy outputs target joint position…
View article: CERBERUS: Autonomous Legged and Aerial Robotic Exploration in the Tunnel and Urban Circuits of the DARPA Subterranean Challenge
CERBERUS: Autonomous Legged and Aerial Robotic Exploration in the Tunnel and Urban Circuits of the DARPA Subterranean Challenge Open
Autonomous exploration of subterranean environments constitutes a major frontier for robotic systems, as underground settings present key challenges that can render robot autonomy hard to achieve. This problem has motivated the DARPA Subte…
View article: CERBERUS: Autonomous Legged and Aerial Robotic Exploration in the Tunnel and Urban Circuits of the DARPA Subterranean Challenge
CERBERUS: Autonomous Legged and Aerial Robotic Exploration in the Tunnel and Urban Circuits of the DARPA Subterranean Challenge Open
Autonomous exploration of subterranean environments constitutes a major frontier for robotic systems, as underground settings present key challenges that can render robot autonomy hard to achieve. This problem has motivated the DARPA Subte…
View article: CERBERUS: Autonomous Legged and Aerial Robotic Exploration in the Tunnel and Urban Circuits of the DARPA Subterranean Challenge
CERBERUS: Autonomous Legged and Aerial Robotic Exploration in the Tunnel and Urban Circuits of the DARPA Subterranean Challenge Open
Autonomous exploration of subterranean environments constitutes a major frontier for robotic systems as underground settings present key challenges that can render robot autonomy hard to achieve. This has motivated the DARPA Subterranean C…
View article: Model-Free Online Motion Adaptation for Energy-Efficient Flight of Multicopters
Model-Free Online Motion Adaptation for Energy-Efficient Flight of Multicopters Open
Limited flight distance and time is a common problem for multicopters. We propose a method for finding the optimal speed and sideslip angle of a multicopter flying a given path to achieve either the longest flight distance or time. Since f…
View article: Team CERBERUS Wins the DARPA Subterranean Challenge: Technical Overview and Lessons Learned
Team CERBERUS Wins the DARPA Subterranean Challenge: Technical Overview and Lessons Learned Open
This article presents the CERBERUS robotic system-of-systems, which won the DARPA Subterranean Challenge Final Event in 2021. The Subterranean Challenge was organized by DARPA with the vision to facilitate the novel technologies necessary …