Ella Atkins

Zhaojian Li, Ilya Kolmanovsky, Ella Atkins et al.

This chapter presents an H-infinity filtering framework for cloud-aided semiactive suspension system with time-varying delays. In this system, road profile information is downloaded from a cloud database to facilitate onboard estimation of suspension states. Time-varying data transmission delays are considered and assumed to be bounded. A quarter-car linear suspension model is used and an H-infinity filter is designed with both onboard sensor measurements and delayed road profile information from the cloud. The filter design procedure is designed based on linear matrix inequalities (LMIs). Numerical simulation results are reported that illustrates the fusion of cloud-based and on-board information that can be achieved in Vehicleto- Cloud-to-Vehicle (V2C2V) implementation.

Odest Chadwicke Jenkins, Jessy Grizzle, Ella Atkins et al.

The Robotics Major at the University of Michigan was successfully launched in the 2022-23 academic year as an innovative step forward to better serve students, our communities, and our society. Building on our guiding principle of "Robotics with Respect" and our larger Robotics Pathways model, the Michigan Robotics Major was designed to define robotics as a true academic discipline with both equity and excellence as our highest priorities. Understanding that talent is equally distributed but opportunity is not, the Michigan Robotics Major has embraced an adaptable curriculum that is accessible through a diversity of student pathways and enables successful and sustained career-long participation in robotics, AI, and automation professions. The results after our planning efforts (2019-22) and first academic year (2022-23) have been highly encouraging: more than 100 students declared Robotics as their major, completion of the Robotics major by our first two graduates, soaring enrollments in our Robotics classes, thriving partnerships with Historically Black Colleges and Universities. This document provides our original curricular proposal for the Robotics Undergraduate Program at the University of Michigan, submitted to the Michigan Association of State Universities in April 2022 and approved in June 2022. The dissemination of our program design is in the spirit of continued growth for higher education towards realizing equity and excellence. The most recent version of this document is also available on Google Docs through this link: https://ocj.me/robotics_major

Matthew Romano, Prince Kuevor, Derek Lukacs et al.

This paper experimentally evaluates continuum deformation cooperative control for the first time. Theoretical results are expanded to place a bounding triangle on the leader-follower system such that the team is contained despite nontrivial tracking error. Flight tests were conducted with custom quadrotors running a modified version of ArduPilot on a BeagleBone Blue in M-Air, an outdoor netted flight facility. Motion capture and an onboard inertial measurement unit were used for state estimation. Position error was characterized in single vehicle tests using quintic spline trajectories and different reference velocities. Five-quadrotor leader trajectories were generated, and followers executed the continuum deformation control law in-flight. Flight tests successfully demonstrated continuum deformation; future work in characterizing error propagation from leaders to followers is discussed.

Hossein Rastgoftar, Ella Atkins

This paper studies collective motion optimization of a fleet of UAVs flying over a populated and geometrically constrained area. The paper treats UAVs as particles of a deformable body, thus, UAV coordination is defined by a homeomorphic continuum deformation function. Under continuum deformation, the distance between individual UAVs can significantly change while assuring the UAVs dont collide, enabling a swarm to travel through the potentially cluttered environment. To ensure inter-agent and obstacle collision avoidance, the paper formulates safety requirements as inequality constraints of the coordination optimization problem. The main objective of the paper is then to optimize continuum deformation of the UAV team satisfying all continuum deformation inequality constraints. Given initial and target configurations, the cost is defined as a weighted sum of the travel distance and distributed cost proportional to the likelihood of the human presence

Yu Yao, Ella Atkins, Matthew Johnson Roberson et al.

Accurate prediction of pedestrian crossing behaviors by autonomous vehicles can significantly improve traffic safety. Existing approaches often model pedestrian behaviors using trajectories or poses but do not offer a deeper semantic interpretation of a person's actions or how actions influence a pedestrian's intention to cross in the future. In this work, we follow the neuroscience and psychological literature to define pedestrian crossing behavior as a combination of an unobserved inner will (a probabilistic representation of binary intent of crossing vs. not crossing) and a set of multi-class actions (e.g., walking, standing, etc.). Intent generates actions, and the future actions in turn reflect the intent. We present a novel multi-task network that predicts future pedestrian actions and uses predicted future action as a prior to detect the present intent and action of the pedestrian. We also designed an attention relation network to incorporate external environmental contexts thus further improve intent and action detection performance. We evaluated our approach on two naturalistic driving datasets, PIE and JAAD, and extensive experiments show significantly improved and more explainable results for both intent detection and action prediction over state-of-the-art approaches. Our code is available at: https://github.com/umautobots/pedestrian_intent_action_detection.

Yu Yao, Xizi Wang, Mingze Xu et al.

Video anomaly detection (VAD) has been extensively studied. However, research on egocentric traffic videos with dynamic scenes lacks large-scale benchmark datasets as well as effective evaluation metrics. This paper proposes traffic anomaly detection with a \textit{when-where-what} pipeline to detect, localize, and recognize anomalous events from egocentric videos. We introduce a new dataset called Detection of Traffic Anomaly (DoTA) containing 4,677 videos with temporal, spatial, and categorical annotations. A new spatial-temporal area under curve (STAUC) evaluation metric is proposed and used with DoTA. State-of-the-art methods are benchmarked for two VAD-related tasks.Experimental results show STAUC is an effective VAD metric. To our knowledge, DoTA is the largest traffic anomaly dataset to-date and is the first supporting traffic anomaly studies across when-where-what perspectives. Our code and dataset can be found in: https://github.com/MoonBlvd/Detection-of-Traffic-Anomaly

Matthew Romano, Yuxin Chen, Owen Marshall et al.

This paper presents the first demonstration of autonomous roofing with a multicopter. A DJI S1000 octocopter equipped with an off-the-shelf nailgun and an adjustableslope roof mock-up were used. The nailgun was modified to allow triggering from the vehicle and tooltip compression feedback. A mount was designed to adjust the angle to match representative roof slopes. An open-source octocopter autopilot facilitated controller adaptation for the roofing application. A state machine managed autonomous nailing sequences using smooth trajectories designed to apply prescribed contact forces for reliable nail deployment. Experimental results showed that the system is capable of nailing within a required three centimeter gap on the shingle. Extensions to achieve a complete autonomous roofing system are discussed as future work.

Juan Paredes, Prashin Sharma, Brian Ha et al.

Quadcopters are increasingly used for applications ranging from hobby to industrial products and services. This paper serves as a tutorial on the design, simulation, implementation, and experimental outdoor testing of digital quadcopter flight controllers, including Explicit Model Predictive Control, Linear Quadratic Regulator, and Proportional Integral Derivative. A quadcopter was flown in an outdoor testing facility and made to track an inclined, circular path at different tangential velocities under ambient wind conditions. Controller performance was evaluated via multiple metrics, such as position tracking error, velocity tracking error, and onboard computation time. Challenges related to the use of computationally limited embedded hardware and flight in an outdoor environment are addressed with proposed solutions.

Prashin Sharma, Ella Atkins

Batteries have been identified as one most likely small UAS (sUAS) components to fail in flight. sUAS safety will therefore be improved with redundant or backup batteries. This paper presents a prognostics-informed Markov Decision Process (MDP) model for managing multi-battery reconfiguration for sUAS missions. Typical lithium polymer (Lipo) battery properties are experimentally characterized and used in Monte Carlo simulations to establish battery dynamics in sUAS flights of varying duration. Case studies illustrate the trade off between multi-battery system increased complexity/weight and resilience to non-ideal battery performance.

Yu Yao, Ella Atkins, Matthew Johnson-Roberson et al.

Pedestrian trajectory prediction is an essential task in robotic applications such as autonomous driving and robot navigation. State-of-the-art trajectory predictors use a conditional variational autoencoder (CVAE) with recurrent neural networks (RNNs) to encode observed trajectories and decode multi-modal future trajectories. This process can suffer from accumulated errors over long prediction horizons (>=2 seconds). This paper presents BiTraP, a goal-conditioned bi-directional multi-modal trajectory prediction method based on the CVAE. BiTraP estimates the goal (end-point) of trajectories and introduces a novel bi-directional decoder to improve longer-term trajectory prediction accuracy. Extensive experiments show that BiTraP generalizes to both first-person view (FPV) and bird's-eye view (BEV) scenarios and outperforms state-of-the-art results by ~10-50%. We also show that different choices of non-parametric versus parametric target models in the CVAE directly influence the predicted multi-modal trajectory distributions. These results provide guidance on trajectory predictor design for robotic applications such as collision avoidance and navigation systems.

Jeremy Castagno, Ella Atkins

Flat surfaces captured by 3D point clouds are often used for localization, mapping, and modeling. Dense point cloud processing has high computation and memory costs making low-dimensional representations of flat surfaces such as polygons desirable. We present Polylidar3D, a non-convex polygon extraction algorithm which takes as input unorganized 3D point clouds (e.g., LiDAR data), organized point clouds (e.g., range images), or user-provided meshes. Non-convex polygons represent flat surfaces in an environment with interior cutouts representing obstacles or holes. The Polylidar3D front-end transforms input data into a half-edge triangular mesh. This representation provides a common level of input data abstraction for subsequent back-end processing. The Polylidar3D back-end is composed of four core algorithms: mesh smoothing, dominant plane normal estimation, planar segment extraction, and finally polygon extraction. Polylidar3D is shown to be quite fast, making use of CPU multi-threading and GPU acceleration when available. We demonstrate Polylidar3D's versatility and speed with real-world datasets including aerial LiDAR point clouds for rooftop mapping, autonomous driving LiDAR point clouds for road surface detection, and RGBD cameras for indoor floor/wall detection. We also evaluate Polylidar3D on a challenging planar segmentation benchmark dataset. Results consistently show excellent speed and accuracy.

Jeremy Castagno, Ella Atkins

This paper presents Polylidar, an efficient algorithm to extract non-convex polygons from 2D point sets, including interior holes. Plane segmented point clouds can be input into Polylidar to extract their polygonal counterpart, thereby reducing map size and improving visualization. The algorithm begins by triangulating the point set and filtering triangles by user configurable parameters such as triangle edge length. Next, connected triangles are extracted into triangular mesh regions representing the shape of the point set. Finally each region is converted to a polygon through a novel boundary following method which accounts for holes. Real-world and synthetic benchmarks are presented to comparatively evaluate Polylidar speed and accuracy. Results show comparable accuracy and more than four times speedup compared to other concave polygon extraction methods.

Nan Li, Yu Yao, Ilya Kolmanovsky et al.

Motivated by the need to develop simulation tools for verification and validation of autonomous driving systems operating in traffic consisting of both autonomous and human-driven vehicles, we propose a framework for modeling vehicle interactions at uncontrolled intersections. The proposed interaction modeling approach is based on game theory with multiple concurrent leader-follower pairs, and accounts for common traffic rules. We parameterize the intersection layouts and geometries to model uncontrolled intersections with various configurations, and apply the proposed approach to model the interactive behavior of vehicles at these intersections. Based on simulation results in various traffic scenarios, we show that the model exhibits reasonable behavior expected in traffic, including the capability of reproducing scenarios extracted from real-world traffic data and reasonable performance in resolving traffic conflicts. The model is further validated based on the level-of-service traffic quality rating system and demonstrates manageable computational complexity compared to traditional multi-player game-theoretic models.

Hossein Rastgoftar, Ella Atkins

This paper develops a novel physics-inspired traffic coordination approach and applies it to Unmanned Aircraft System (UAS) traffic management. We extend available physics-inspired approaches previously applied to 1-D traffic flow on highways and urban streets to support models of traffic coordination in higher dimension airspace for cases where no predefined paths exist. The paper considers airspace as a finite control volume while UAS coordination, treated as continuum deformation, is controlled at the airspace boundaries. By partitioning airspace into planned and unplanned spaces, the paper models nominal coordination in the planned airspace as the solution of a partial differential equation with spatiotemporal parameters. This paper also improves resilience to vehicle failures with a resilient boundary control algorithm to update the geometry of the planned space when UAS problems threaten safe coordination in existing navigable airspace channels. To support UAS coordination at the microscopic level, we propose clustering vehicles based on vehicle performance limits. UAS clusters, with each UAS treated as a particle of a virtual rigid body, use leader-follower containment to acquire the macroscopic desired trajectory.

Jeremy Castagno, Yu Yao, Ella Atkins

Safe autonomous landing in urban cities is a necessity for the growing Unmanned Aircraft Systems (UAS) industry. In urgent situations, building rooftops, particularly flat rooftops, can provide local safe landing zones for small UAS. This paper investigates the real-time identification and selection of safe landing zones on rooftops based on LiDAR and camera sensor feedback. A visual high fidelity simulated city is constructed in the Unreal game engine, with particular attention paid to accurately generating rooftops and the common obstructions found thereon, e.g., ac units, water towers, air vents. AirSim, a robotic simulator plugin for Unreal, offers drone simulation and control and is capable of outputting video and LiDAR sensor data streams from the simulated Unreal world. A neural network is trained on randomized simulated cities to provide a pixel classification model. A novel algorithm is presented which finds the optimum obstacle-free landing position on nearby rooftops by fusing LiDAR and vision data.