Navigation and obstacle avoidance in aquatic en-vironments for autonomous surface vehicles (ASVs) in high-traffic maritime scenarios is still an open challenge, as the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) is not defined for multi-encounter situations. Current state-of-the-art methods resolve single-to-single encounters with sequential actions and assume that other obstacles follow COLREGs. Our work proposes a novel real-time non-myopic obstacle avoidance method, allowing an ASV that has only partial knowledge of the surroundings within the sensor radius to navigate in high-traffic maritime scenarios. Specifically, we achieve a holistic view of the feasible ASV action space able to avoid deadlock scenarios, by proposing (1) a clustering method based on motion attributes of other obstacles, (2) a geometric framework for identifying the feasible action space, and (3) a multi-objective optimization to determine the best action. Theoretical analysis and extensive realistic experiments in simulation considering real-world traffic scenarios demonstrate that our proposed real-time obstacle avoidance method is able to achieve safer trajectories than other state-of-the-art methods and that is robust to uncertainty present in the current information available to the ASV.
more »
« less
Risk Vector-based Near miss Obstacle Avoidance for Autonomous Surface Vehicles
This paper presents a novel risk vector-based near miss prediction and obstacle avoidance method. The proposed method uses the sensor readings about the pose of the other obstacles to infer their motion model (velocity and heading) and, accordingly, adapt the risk assessment and take corrective actions if necessary. Relative vector calculations allow the method to perform in real-time. The algorithm has 1.68 times faster computation performance with less change of motion than other methods and it enables a robot to avoid 25 obstacles in a congested area. Fallback behaviors are also proposed in case of faulty sensors or situation changes. Simulation experiments with parameters inferred from experiments in the ocean with our custom-made robotic boat show the flexibility and adaptability of the proposed method to many obstacles present in the environment. Results highlight more efficient trajectories and comparable safety as other state-of-the-art methods, as well as robustness to failures.
more »
« less
- NSF-PAR ID:
- 10224192
- Date Published:
- Journal Name:
- 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- Page Range / eLocation ID:
- 1805 to 1812
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Goal: Lifting is a common manual material handling task performed in the workplaces. It is considered as one of the main risk factors for work-related musculoskeletal disorders. An important criterion to identify the unsafe lifting task is the values of the net force and moment at L5/S1 joint. These values are mainly calculated in a laboratory environment, which utilizes marker-based sensors to collect three-dimensional (3-D) information and force plates to measure the external forces and moments. However, this method is usually expensive to set up, time-consuming in process, and sensitive to the surrounding environment. In this study, we propose a deep neural network (DNN)-based framework for 3-D pose estimation, which addresses the aforementioned limitations, and we employ the results for L5/S1 moment and force calculation. Methods: At the first step of the proposed framework, full body 3-D pose is captured using a DNN, then at the second step, estimated 3-D body pose along with the subject's anthropometric information is utilized to calculate L5/S1 join's kinetic by a top-down inverse dynamic algorithm. Results: To fully evaluate our approach, we conducted experiments using a lifting dataset consisting of 12 subjects performing various types of lifting tasks. The results are validated against a marker-based motion capture system as a reference. The grand mean ± SD of the total moment/force absolute errors across all the dataset was 9.06 ± 7.60 N·m/4.85 ± 4.85 N. Conclusion: The proposed method provides a reliable tool for assessment of the lower back kinetics during lifting and can be an alternative when the use of marker-based motion capture systems is not possible.more » « less
-
This work considers a Motion Planning Problem with Dynamic Obstacles (MPDO) in 2D that requires finding a minimum-arrivaltime collision-free trajectory for a point robot between its start and goal locations amid dynamic obstacles moving along known trajectories. Existing methods, such as continuous Dijkstra paradigm, can find an optimal solution by restricting the shape of the obstacles or the motion of the robot, while this work makes no such assumptions. Other methods, such as search-based planners and sampling-based approaches can compute a feasible solution to this problem but do not provide approximation bounds. Since finding the optimum is challenging for MPDO, this paper develops a framework that can provide tight lower bounds to the optimum. These bounds act as proxies for the optimum which can then be used to bound the deviation of a feasible solution from the optimum. To accomplish this, we develop a framework that consists of (i) a bi-level discretization approach that converts the MPDO to a relaxed path planning problem, and (ii) an algorithm that can solve the relaxed problem to obtain lower bounds. We also present numerical results to corroborate the performance of the proposed framework. These results show that the bounds obtained by our approach for some instances are up to twice tighter than a baseline approach showcasing potential advantages of the proposed approach.more » « less
-
more » « less
Abstract Predicting where crop pests and diseases can occur, both now and in the future under different climate change scenarios, is a major challenge for crop management. One solution is to estimate the fundamental thermal niche of the pest/disease to indicate where establishment is possible. Here, we develop methods for estimating and displaying the fundamental thermal niche of pests and pathogens and apply these methods to Huanglongbing (HLB), a vector‐borne disease that is currently threatening the citrus industry worldwide.
We derive a suitability metric based on a mathematical model of HLB transmission between tree hosts and its vector
Diaphorina citri , and incorporate the effect of temperature on vector traits using data from laboratory experiments performed at different temperatures. We validate the model using data on the historical range of HLB.Our model predicts that transmission of HLB is possible between 16 and 33°C with peak transmission at ~25°C. The greatest uncertainty in our suitability metric is associated with the mortality of the vectors at peak transmission, and fecundity at the edges of the thermal range, indicating that these parameters need further experimental work.
We produce global thermal niche maps by plotting how many months each location is suitable for establishment of the pest/disease. This analysis reveals that the highest suitability for HLB occurs near the equator in large citrus‐producing regions, such as Brazil and South‐East Asia. Within the Northern Hemisphere, the Iberian peninsula and California are HLB suitable for up to 7 months of the year and are free of HLB currently.
Policy implications . We create a thermal niche map which indicates the places at greatest risk of establishment should a crop disease or pest enter these regions. This indicates where surveillance should be focused to prevent establishment. Our mechanistic method can be used to predict new areas for Huanglongbing transmission under different climate change scenarios and is easily adapted to other vector‐borne diseases and crop pests. -
null (Ed.)Falls affect a growing number of the population each year. Clinical methods to assess fall risk usually evaluate the performance of specific motions such as balancing or Sit-to-Stand. Unfortunately, these techniques have been shown to have poor predictive power, and are unable to identify the portions of motion that are most unstable. To this end, it may be useful to identify the set of body configurations that can accomplish a task under a specified control strategy. The resulting strategy-specific boundary between stable and unstable motion could be used to identify individuals at risk of falling. The recently proposed Stability Basin is defined as the set of configurations through time that do not lead to failure for an individual under their chosen control strategy. This paper presents a novel method to compute the Stability Basin and the first experimental validation of the Stability Basin with a perturbative Sit-to-Stand experiment involving forwards or backwards pulls from a motor-driven cable with 11 subjects. The individually-constructed Stability Basins are used to identify when a trial fails, i.e. when an individual must switch from their chosen control strategy (indicated by a step or sit) to recover from a perturbation. The constructed Stability Basins correctly predict the outcome of trials where failure was observed with over 90 % accuracy, and correctly predict the outcome of successful trials with over 95 % accuracy. The Stability Basin was compared to three other methods and was found to estimate the stable region with over 45 % more accuracy in all cases. This study demonstrates that Stability Basins offer a novel model-based approach for quantifying stability during motion, which could be used in physical therapy for individuals at risk of falling.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/IROS45743.2020.9341105
