2021 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.
2021 Day 1 - May 10
| 9:00 AM | Welcome & Opening Remarks (Day 1 - Main Hall) |
|
Bogdan Epureanu |
David Gorsich |
|
The Honorable Gary Peters (Day 1 - Main Hall) Dr. Alec D. Gallimore (Day 1 - Main Hall) |
||
| 9:25 | Keynote: (Day 1 - Main Hall) Michael Cadieux |
|
| 9:45 | Keynote: (Day 1 - Main Hall) Christopher Davey |
|
| 10:05 | Break |
|
| 10:15 |
There is no "I" in Team: Optimal task allocation in human-autonomy teaming Abstract: Autonomous vehicles are increasingly thought of as team members alongside humans in both military and civilian applications. Such autonomous agents are capable of handling dangerous tasks but are limited in their reactions to unforeseen events. At the same time, humans have more adaptive and creative problem-solving skills but are limited in terms of handling some specific tasks and managing cognitive loads. The inclusion of autonomy within a team requires a significant effort to train the agents and dynamically distribute tasks among the agents to perform optimally during operations. In this case study, we brought together three projects and constructed a unique framework to train a team of heterogeneous agents, composed of both humans and autonomous agents, to reliably perform tasks in uncertain environments. A computational trust model for multi-agent teams was created and deployed in trust-based path planning algorithms. The cost and limitations of the mobility of the agents was accounted for when training the team in a synthetic environment. An artificial intelligence algorithm was then developed for autonomous agents to learn how to collaborate with humans and other autonomous agents through reinforcement learning. To showcase the application of the developed algorithms, a disaster relief scenario was simulated in a high-fidelity game engine environment where a human interacts with the environment in real-time using virtual reality. An adaptive algorithm was developed to assist the humans in their decision-making and improve their performance by continuously evaluating the human’s cognitive task loads. The heterogeneity of the team was described by the differences in agent capabilities of task handling, sensing, and communication, as well as the level of risk aversion in humans’ decision-making processes. Results of this study show that the trained autonomous agents using the developed algorithms can reliably collaborate with humans and clear all the assigned tasks in a complex environment. In this study, the team performance when the human-autonomy communication used an adaptive interface based on a data-driven cognitive task load model increased by over 180% compared to a heuristic interface, and over 72% compared to a fixed and most detailed interface. The proposed framework is a basis for further developments and design of human-autonomy teams. |
|
| 11:00 | Break |
|
| 11:10 | Technical Session 1 |
|
|
Session Chairs: |
Session Chairs: |
|
| 11.10 AM | 1.25 A Decision-Based Mobility Model for Semi and Fully Autonomous Vehicles PI: Vijitashwa Pandey |
1.28 Robust Terrain Identification and Path Planning for Autonomous Ground Vehicles in Unstructured Environments PI: Jeremy Bos |
| 11.30 AM | 2.12 Cognitive Modeling of Human Operator Behavior During Interaction With Autonomous Systems PI: Tulga Ersal |
1.32 Tensor data compression and dimensionality reduction for autonomous mobility PI: Shravan Veerapaneni |
| 11.50 AM | 5.20 Dynamic Teaming of Autonomous Vehicles to Address Intelligent Adversarial Actions PI: Bogdan Epureanu |
5.14 Advances in computation of safety envelopes for autonomous systems PI: Necmiye Ozay |
| 12.10 PM | 5.19 Adversarial Scene Generation PI: Ram Vasudevan |
5.15 Integrating Safe Learning into Supervisory Limit Protection for Autonomous Vehicular Systems PI: Ilya Kolmanovsky, Anouck Girard |
| 12:30 PM | Break | |
| 1:30 | Poster Session 1 (scroll down for roster) | |
| 2:45 | Poster Session 2 (scroll down for roster) | |
| 4:00 | Adjourn, Day 1 | |
2021 Day 2 - May 11
| 9:00 AM | Introductions (Day 2 - Main Hall) Kira Barton & Ram Vasudevan |
|
| 9:05 | Keynote: (Day 2 - Main Hall) Dr. Patrick Baker |
|
| 9:25 | Keynote: (Day 2 - Main Hall) Tony Bromwell |
|
| 9:45 | Keynote: (Day 2 - Main Hall) Kevin Dutcher |
|
| 10:05 | Break | |
| 10:15 |
Right Resources, Right Place, Right Time: Using real-time physics-based simulation to optimize high-level mission planning under uncertainty Abstract: As Army vehicles become more intelligent with autonomous behaviors, planning their missions under uncertainties becomes more complex. On the one-hand, low-level `path planning algorithms’ solve the challenge of finding an optimal trajectory between a pair of source and destination while considering obstacles, and provide closed-loop control signals to each vehicle so that they can follow the trajectory with minimum deviations. On the other hand, a high-level ‘mission planning algorithm’ provides the sequence of visits for the vehicle while considering points of interests, environment uncertainties, and other operational constraints. Though these low-level and high-level algorithms work in tandem, due to overwhelming complexities, the research works have traditionally been done independent to each other. In this case study, we address this gap by bringing two ARC projects together to integrate real-time physics-based simulation of autonomous ground vehicles with high-level mission planning algorithms. The summary of the case study are as follows: best and worst scenarios inferred from data summarization may not necessarily be the best and worst scenarios for mission planning; for a fixed importance of distance and HRI costs, the mission plan across scenarios from low-level planning may change, and this is specifically observed in scenarios with lower goal speed. The deviations in mission plan due to scenarios is around 25%; and also, deviations within scenarios due to weights for distance and HRI costs is at 35%. These imply the importance of synergy between low-level and high-level planning algorithms. |
|
| 11:00 | Break | |
| 11:10 | Technical Session 2 - Part I |
|
|
Session Chairs: |
Session Chairs: |
|
| 11.10 AM | 1.35 Novel Algorithms for Multi-Agent Autonomous Telerobotic Surveillance and Reconnaissance System PI: Manish Bansal |
3.A84 Split Traction Characteristic Analytics and Digital Image Correlation (DIC) Strain Analysis PI: Lee Moradi |
| 11.30 AM | 1.27 Mutually-Aaptive Shared Control Between Human Operators and Autonomy in Ground Vehicles PI: Tulga Ersal |
3.17 Enhanced Multiscale Off‐Road Mobility Prediction Capability with Machine Learning Constitutive Modeling for Large Deformable Granular Terrain PI: Hiroyuki Sugiyama |
| 11.50 AM | 5.16 Resilient Teaming: Fleet organization and decision making in heterogeneous vehicle teams PI: Kira Barton |
1.29 Characterizing the Terrain Strength and Type Using Remote Sensing for Mobility PI: Thomas Oommen |
| 12:10 PM | Break | |
| 12:20 PM | Technical Session 2 - Part II |
|
|
Session Chairs: |
Session Chairs: |
|
| 12.20 PM | 1.34 Processing Image Data from Unstructured Environments PI: Nick Vlahopoulos |
4.34 Discovery of Salt Hydrates for Thermal Energy Storage PI: Donald Siegel |
| 12.40 PM | 5.17 Communication-Constrained Multi-Robot Coordination PI: Ed Olson |
5.18 Probability of Mobility for Mission Planning of Autonomous Ground Vehicles at “High Stress” Environments" PI: Zissimos Mourelatos, Zhen Hu |
| 1.00 PM | Best Lightning Talk Competition Finalists Announced by Andre Boehman |
2.A72 Assessing the Quality of Driving of Off-Road Vehicles: A Set of Test Courses for the U.S. Army PI: Paul Green |
| 1:20 | Awards and Closing | |
Bogdan Epureanu |
David Gorsich |
|
| 1:30 | Adjourn, Day 2 | |
| Posters and Lightning Talks |
|---|
| Poster 1.25 A Decision-Based Mobility Model for Semi and Fully Autonomous Vehicles |
| Poster 1.27 Mutually-Adaptive Shared Control between Human Operators and Autonomy in Ground Vehicles |
| Poster 1.28 Robustness Evaluation of Point-Cloud Based Path Planning and Navigation |
| Poster 1.29 Characterizing the Terrain Strength and Type Using Remote Sensing for Mobility
Jordan Ewing is a Finalist of the Best Student Lightning Talk Competition |
| Poster 1.30 Multi-Objective Optimization Approach for Multi-Vehicle Path Planning Problems considering Human-Robot Interactions |
| Poster 1.31 Evaluating Sensitivity of Autonomous Algorithms to Sensor Error and Environmental Conditions |
| Poster 1.32 Tensor Data Compression and Dimensionality Reduction for Autonomous Mobility |
| Poster 1.33 Trust-based Symbolic Motion and Task Planning for Multi-robot Bounding Overwatch |
| Poster 1.34 Processing Image Data from Unstructured Environments |
| Poster 1.35 Novel Algorithms for Multi-Agent Autonomous Telerobotic Surveillance and Reconnaissance System |
| Poster 1.36 A robust semantic-aware perception system using proprioception, geometry, and semantics in unstructured and unknown environments |
| Poster 1.37 Ultrasound based perception using ML algorithms trained in synthetic environments |
| Poster 1.A73 Quantum Computing for Offroad Mobility |
| Poster 1.A75 Agile Modular Cyber-Physical Vehicle Platforms |
| Poster 1.A81 Behavior Cloning in Atari Games Using a Combined Variational Autoencoder and Predictor Model |
| Poster 1.A82 A Hybrid Controller with Observation and Decision Making for Autonomous Mobility Control System |
| Poster 1.A83 Rapid High-dimensional Semantic Segmentation With Echo State Networks Steven Gardner is a Finalist of the Best Student Lightning Talk Competition |
| Poster 1.A85 Autonomous Vehicle Interactive Dynamics and Morphing with Mobility & Maneuver Self-Learning-and-Improvement |
| Poster 1.A89 Terrain Adaptive Autonomous Vehicles for Uncertain Off-Road Environments |
| Poster 2.12 Cognitive Modeling of Human Operator Behavior during Interaction with Autonomous Systems |
| Poster 2.13 Optimal Distribution of Tasks in Human-Autonomy Teams |
| Poster 2.14 Dynamic Task Allocation and Understanding of Situational Awareness Under Different Levels of Autonomy in Closed-Hatch Military Vehicles Jessie E. Cossitt is the Winner of the Best Student Lightning Talk Competition |
| Poster 2.15 In-the-wild Question Answering: Toward Natural Human-Autonomy Interaction |
| Poster 2.16 Language Communication and Collaboration with Autonomous Vehicles Under Unexpected Situations |
| Poster 2.A72 Assessing the Quality of Driving of Off-Road Vehicles: A Set of Test Courses for the U.S. Army |
| Poster 3.17 Enhanced Multiscale Off‐Road Mobility Prediction Capability with Machine Learning Constitutive Modeling for Large Deformable Granular Terrain |
| Poster 3.18 Materials design of polycarbonates at the atomistic scale with machine learning |
| Poster 3.A84 Instant Tire Slippage Characterization with Digital Image Correlation (DIC) for Autonomous Mobility Applications |
| Poster 3.A86 Assessment and Virtualization of Tire-Soft Soil Interactions for Real-Time Evaluation and Control of Autonomous Vehicle Mobility |
| Poster 3.A88 Technical Approached and Analysis of Vehicle Conceptual Design for Mobility and Autonomous Mobility |
| Poster 4.34 Discovery of Salt Hydrates for Thermal Energy Storage |
| Poster 4.36 Learning Enabled Mission Adaptation for a Hybrid Opposed Piston Engine Joseph Drallmeier is a Finalist of the Best Student Lightning Talk Competition |
| Poster 4.A76 Integrated Transient Control and Thermal Management of Autonomous Off-Road Vehicle Propulsion Systems |
| Poster 4.A87 Maximizing Autonomous Mobility and Energy Efficiency on-the-go through Exteroceptive and Proprioceptive Self-Learning-and-Improvement |
| Poster 5.14 Safe Online Planning in Unknown Environments |
| Poster 5.15 Autonomously Learning Mobility Limits |
| Poster 5.16 Robust Task Scheduling for Heterogeneous Robot Teams under Capability Uncertainty Bo Fu is a Finalist of the Best Student Lightning Talk Competition |
| Poster 5.17 Communication-Constrained Multi-Robot Coordination |
| Poster 5.18 Probability of Mobility for Mission Planning of Autonomous Ground Vehicles at “High Stress” Environments |
| Poster 5.19 Adversarial Scene Generation for Virtual Validation and Testing of AV Performance Ted Sender is a Finalist of the Best Student Lightning Talk Competition |
| Poster 5.20 Collaboration, cooperation and competition of independent and intelligent agents |
| Poster 5.A71 Virtual Prototyping Capabilities by ADAS Tools Connected with a Gaming Engine |
| Poster 5.A77 Energy Management of Multi-Scale Vehicles |
| Poster 5.A78 Virtual Prototyping & Digital Engineering for Autonomy-enabled Gorund Vehicles - System-Level Requirements Definition |
| Poster 5.A79 Simulation Model Repository and Integration Architecture |
| Poster 5.A80 Tradespace Analysis, Optimization & Decision-Making |
In accordance with Cooperative Agreement W56HZV-19-2-0001 U.S. Army Combat Capabilities Development Command Ground Vehicle Systems Center Warren, MI
Contact: arc-event-inquiries@umich.edu