2023 ARC Annual Review
Welcome! The Automotive Research Center presents this event to bring together members of the automotive research community from across academia, government and industry to share our latest research developments. It is an opportunity to share ideas, discuss Army-relevant efforts, and to leverage and transfer our efforts to industry.
Agenda
2023 Day 1 - May 9
Breakfast from 8:00-9:00 AM
| 9:00 AM | Opening Remarks (room 1060) The Honorable Gary Peters Michael Cadieux |
| 9:15 | Keynote: COL Jeffrey Jurand |
| 9:50 | Keynote: Dr. Mario Santillo |
| 10:25 | Break |
| 10:45 | Case Study: Ultrasound-based perception systems replicating the biosonar capabilities of animals such as bats and marine mammals (Project #1.37) are effective at creating labeled maps of their surroundings in adverse weather. They are also significantly stealthier compared to the ubiquitous LIDAR- and radar-based systems and are relatively inexpensive while having low power consumption. In addition, since sound in air is mostly influenced by object geometry and less by material properties, it is significantly more difficult to develop countermeasures for sound-based perception methods (for instance, by judicious choice of target coating) than it is for electromagnetic-based systems such as LIDAR, radar, and video cameras. Nevertheless, sound-based countermeasures have been actively pursued. For example, cloaking structures capable of changing the objects' echoic signatures and be deployable on-demand in a small amount of time are already being investigated in the ARC (Project #3.21). This presentation highlights the lessons learned from pitting the perception system against the cloak and the possible improvements of these two adversaries. |
| 11:30 | Case Study: Off-road navigation of autonomous vehicles presents far more stringent requirements than road terrains due to the vast variation of scenes caused by chaotic, unorganized, and natural geographical features and objects. Optimal autonomous navigation requires a perception system be accurate, precise, and require low computational effort to enable navigation and maneuverability at tactically relevant speeds. We have explored both image and lidar based semantic segmentation approaches to determine estimated trafficability of off-road environments which can be used to generate cost maps and occupancy grids to enable autonomous path planning. After evaluation and comparison, an image-based convolutional neural network architecture was selected for segmentation and classification. To better optimize the perception system’s performance in the context of a relevant application, we integrated our perception solution with the NATO Autonomy Stack and performed test and evaluation iterations with the NATO AVT-341 Loyal Wingman Scenario. Iterations focused on strategies to (1) increase accuracy through composition of machine learning training datasets, (2) integration details to reduce computational effort, and (3) workflows for different sensor sets. |
| 12:15 PM | Lunch (atrium) |
| 1:30 | Technical Session 1 (see matrix of parallel sessions) |
Session 1.A (room 1060) and Session 1.B (room 1050) |
|
| 3:30 | Poster Session and Reception (atrium) |
| 6:30 | Adjourn, Day 1 |
2023 Day 2 - May 10
Breakfast from 8:00-9:00 AM
| 9:00 AM | Day 2 Opening Remarks Dr. Eric Michielssen Dr. David Gorsich |
| 9:10 | Keynote: Dr. Paramsothy Jayakumar Autonomous ground systems are a crucial part of the future military strategy and off-road mobility is a key measure of their performance. However, there is still a lack of understanding of, and metrics for the capabilities and reliability of these new technologies. How fast and reliably can a system reach its destination under a wide range of conditions? How well can it maneuver with soldiers under a variety of operations? Inability to answer such questions hinders fully fielding and operationalizing these systems. Therefore, the NATO Science and Technology Organization’s Advanced Vehicle Technology Panel has commissioned a Research Task Group, NATO AVT-341, to define methods and tools to assess off-road mobility of autonomous military ground systems. |
| 9:45 | Panel Session: Panelists: Dr. Cinzia Cirillo Dr. Matthew Johnson-Roberson Moderator: Over the past year, the race to develop and deploy self-driving systems has been faced with critical challenges and several important questions loom large: How will the benefits of autonomous driving be shared with the public and deployed in the defense context? What regulatory mechanisms are needed to ensure the safety and reliability of these cutting-edge systems? What career opportunities will emerge in this space over the next five, ten, and twenty years? In the face of these challenges, this panel will take a deep dive into the current state of autonomy. Our experts will share insights on the latest technological advancements, explore the regulatory landscape, and examine what the job market in the autonomy space will look like. Join us as we navigate the road ahead and shed light on the future of self-driving vehicles. |
| 10:30 | Break |
| 10:45 | Technical Session 2 (see matrix of parallel sessions) |
Session 2.A (room 1060) and Session 2.B (room 1050) |
|
| 12:45 PM | Break |
| 1:00 - 3:30 | Awards & Lunch Reception (Atrium) Announcing Winners of Best Student Poster Competition |
| 1:30 - 3:30 |
One-on-One Info Session with GVSC Thrust Area Leaders (room 1060) Dr. Jonathon Smereka, Thrust Area 1 Co-leader Please email arc-event-inquiries@umich.edu to reserve a time-slot. |
| 3:00 - 3:30 |
Access to and Use of the Robotic Technology Kernel (RTK) in ARC Projects (room 1050) Dr. Jonathon Smereka RTK is an Army S&T autonomy software library of tested, vetted, managed, inter-compatible ROS packages which together establish a de facto common robotics platform and can be combined to form parts or all of an "autonomy kit/stack" for ground robots. This talk will introduce what RTK is, discuss the goals, and identify what is required for partners to work directly with the RTK software and material. |
| 3:30 | Day 2 Adjourns |
Technical Talks Matrix
The Technical Talks allow ARC projects to report on their research goals and outcomes. Each talk will consist of a 15-minute presentation followed by 5-minute for Q&A.
2023 Day 1 - May 9
Technical Session 1
Session 1.A | Session 1.B | |
| 1:30 | Project 1.36, PIs: Ghaffari, Barton Convolutional Bayesian Kernel Inference for Real-Time 3D Semantic Mapping | Project 2.15, PI: Mihalcea In-the-wild Question Answering: Toward Natural Human-Autonomy Interaction |
| 1:50 | Project 1.38, PI: Carruth Automated Recognition of Distorted and Obscured Perceptual Sensor Data | Project 2.16, PI: Chai Language Communication and Collaboration with Autonomous Vehicles Under Unexpected Situations |
| 2:10 | Project 3.17, PI: Sugiyama Enhanced Multiscale Off‐Road Mobility Prediction Capability with Machine Learning Constitutive Modeling for Large Deformable Granular Terrain | Project 2.17, PIs: Tilbury, Robert Estimating and Calibrating Situation Awareness for Improving Human-Robot Teaming Performance |
| 2:30 | Project 1.34, PI: Vlahopoulos Unsupervised Clustering for Image Data |
Project 1.33, PI: Wang Trust-based Symbolic Motion and Task Planning for Multi-robot Bounding Overwatch |
| 2:50 | Project 3.21, PI: Filipov Design of Modular Origami Structures for Multifunctional Cloaking and Protection |
Project 2.12, PI: Ersal Cognitive Modeling of Human Operator Behavior during Interaction with Autonomous Systems |
| 3:10 - 3:30 | Project 3.18, PI: Barrett Materials Design of Polycarbonates at the Atomistic Scale with Machine Learning | Project 2.13, PI: Epureanu Optimal Distribution of Tasks in Human-Autonomy Teams: Bayesian Online Strategy Adaptation in Open-world Novelty |
2023 Day 2 - May 10
Technical Session 2
Session 2.A |
Session 2.B |
|
| 10:45 | Project 3.20, PIs: Martin, Harwood, Sugiyama Modeling of a Ground Vehicle Operating in Shallow Water |
Project 5.19, PIs: Vasudevan, Epureanu Adversarial Scene Generation for Virtual Validation and Testing of Off-Road Autonomous Vehicle Performance |
| 11:05 | Project 3.22, PIs: Sandu, Yerro-Colom Application of Terramechanics to the Physics-based Modeling of Large Deformations in Undrained Saturated Clay–lugged Tire Interaction |
Project 1.A81, PIs: Gorodetsky, Veerapaneni Incremental Tensor-network Compression: With Applications to Feature Extraction for Behavioral Cloning and Inverse Problems |
| 11:25 | Project 3.19, PI: Lu Intelligent Ultrasound to Adaptively Control Interfacial Properties and Reactions |
Project 1.35, PI: Bansal Adversarial Telerobotic Camera View-Frames Placement and Shortest Path Problems with Distributional Ambiguity |
| 11:45 | Project 4.37, PI: Naber Risk Averse Vehicle Energy, Thermal Signature Management and Control to Enable Silent Mobility/Watch |
Project 2.A92, PI: Louie A Virtual Spectator System for a Multi-User Video Game Environment |
| 12:05 PM | Project 1.A90, PIs: Mourelatos, Hu Efficient Data-Driven Mobility Model Construction for Mission Planning Considering Uncertainty |
Project 2.14, PI: Carruth, Bethel Evaluating Driver Performance, Situation Awareness, and Cognitive Load at Different Levels of Partial Autonomy with Dynamic Task Allocation |
| 12:25 - 12:45 | Project 1.A73, PI: Veerapaneni Warm-starting Quantum Approximate Optimization Algorithm | Project 2.A72/74, PI: Green Assessing the Quality of Driving On and Off-Road Vehicles: Measures and Statistics of Driving Performance |
Poster Session
Every ongoing ARC project contributes to the poster session. It is an excellent opportunity to interact with researchers and network.
1.33 Trust-based Symbolic Task and Motion Planning for Multi-Robot Bounding Overwatch
1.34 Processing Image Data from Unstructured Environments
1.35 Novel Algorithms for Autonomous Telerobotic Surveillance and Reconnaissance System
1.36 Robust Real-Time 3D Semantic Mapping in Off-Road Environments (Runner-up for Best Student Poster Competition - Joey Wilson)
1.37 Ultrasound Based Perception Using ML Algorithms Trained in Synthetic Environments
1.38 Recognizing and Reconstructing Distorted and Obscured Perceptual Sensor Data Resulting from Soiling of the Sensor
1.39 Adaptive and Efficient Perception for Autonomous Ground Vehicles Operating in Highly Stochastic Environments under Sensing Uncertainties (Winner of Best Student Poster Competition - Trier Mortlock)
1.40 Real-time Prediction of Dynamic Vegetation Override for AGV
1.41 Resilient Trajectory Planning for Extreme Mobility on Challenging Slopes (Finalist for Best Student Poster Competition - James Baxter)
1.A73 Warm-started quantum approximate optimization algorithm
1.A81 Tensor Network Approaches for Fast and Data Efficient Learning: Applications to Imitation Learning from Video Data
1.A90 Reliable Deep Learning for Data-Driven Mobility Prediction under Uncertainty for Off-Road Autonomous Ground Vehicles
1.A91 Physics-based Robust, Adaptive and Scalable Control Algorithms for UGVs Operating at High-Speed in Adversarial Environments
1.A100 Rapid and Adaptive Perception Autonomy for Context-Specific Classifications
1.A107 Active Stability Control for Terrain-Adaptive Lightweight-Body Vehicles
1.A108 Self-Powered Wireless Sensing Platform for Vehicle Attitude Control
2.12 Cognitive Modeling of Human Operator Behavior during Interaction with Autonomous Systems
2.13 Optimal Distribution of Tasks in Human-Autonomy Teams: Bayesian Online Strategy Adaptation in Open-world Novelty
2.14 Dynamic Task Allocation and Understanding of Situation Awareness Under Different Levels of Autonomy in Closed-Hatch Military Vehicle
2.15 In-the-wild Question Answering: Toward Natural Human-Autonomy Interaction
2.16 Language Communication and Collaboration with Autonomous Vehicles Under Unexpected Situations
2.17 Investigating the Impacts of Shared Mental Models and Communication on Team Situational Awareness and Performance in Human-Robot Teaming
2.18 Investigating Required Transparency Information and Display Features through an Empirical Study using a Dual-tasks HAT Simulation
2.A72 Driving Performance Measures and Statistics: Definitions and Data
2.A92 Examining Differences in Human Behavior Between Virtual and Real Environments in a Human Robot Teaming Task
2.A94 Situational Awareness & Trust Repair in Multi-Agent Human-Automation Teams
2.A101 Communication, Reaction, & Effectiveness in Warfare (CREW)
3.17 Enhanced Multiscale Off-Road Mobility Prediction Capability with Machine Learning Constitutive Modeling for Large Deformable Granular Terrain
3.18 Materials design of polycarbonates at the atomistic scale with machine learning
3.19 Intelligent ultrasound to adaptively control interfacial properties and reactions (Finalist for Best Student Poster Competition - Ganghyeok Im, Derek Barnes)
3.20 Modeling of a Ground Vehicle Operating in Shallow Water
3.21 Design of Modular Origami Structures for Multifunctional Cloaking and Protection
3.22 Tire–mud interaction modeled using Smoothed Particle Hydrodynamics and Finite Element Analysis (SPH-FEA) techniques and experimental validation
3.23 Adaptive Structures with Embedded Autonomy for Advancing Ground Vehicles
3.A95 Self-sealing process modeling of a multilayer polymer coating system for fuel tanks subjected to a foreign object damage
3.A96 Additively manufactured all-metallic metamaterial solutions for protection of electronic systems in autonomous vehicles
3.A102 Flow-Induced Fabric Dynamics and Thermal Behavior of a Fabric-Covered Vehicle
3.A103 Evaluation of Under-body Blast Response to Loading from Alternative Terra-Medium Environments
3.A111 Integration of stitched Bowtie Antennas on S-glass
3.A112 Advanced Manufacturing, Structural Joining, & Health Monitoring
4.37 Risk Averse Vehicle Signature Management And Control To Enable Silent Mobility/Watch
4.A76 Integrated Transient Control and Thermal Management of Autonomous Off-Road Vehicle Propulsion Systems
4.A105 De Novo Design of Energy Storage Materials Through a Synergistic Approach
4.A106 Novel Materials for Water Treatment in the Battlefield
4.A109 Develop lightweight, low-temperature, and safe batteries
4.A110 Lightweight Electric Powertrain with High-Speed Machines and Drives
5.19 Adversarial Scene Generation for Virtual Validation and Testing of Off-Road Autonomous Vehicle Performance
5.22 Unsupervised Testing and Verification for Software Systems of Ground Autonomous Vehicles
5.23 Automated Co-Design of Vehicles and their Teaming Operations for Optimal Off-Road Performance
5.104 Modular Closed-loop, Real-time, Physics-based Software Simulator for Unmanned Ground Vehicles in Unstructured Terrain Environments
IE.01 Training Review with a Virtual Spectator Interface for Improving Human-Robot Team Performance