The capability to detect objects is a core part of autonomous driving. Due to sensor noise and incomplete data, perfectly detecting and localizing every object is infeasible. Therefore, it is important for a detector to provide the amount of uncertainty in each prediction. Providing the autonomous system with reliable uncertainties enables the vehicle to react differently based on the level of uncertainty. Previous work has estimated the uncertainty in a detection by predicting a probability distribution over object bounding boxes. In this work, we propose a method to improve the ability to learn the probability distribution by considering the potential noise in the ground-truth labeled data. Our proposed approach improves not only the accuracy of the learned distribution but also the object detection performance.
Abstract-Autonomous navigation in outdoor environments with vegetation is difficult because available sensors make very indirect measurements on quantities of interest such as the supporting ground height and the location of obstacles. We introduce a terrain model that includes spatial constraints on these quantities to exploit structure found in outdoor domains and use available sensor data more effectively. The model consists of a latent variable that establishes a prior that favors vegetation of a similar height, plus multiple Markov random fields that incorporate neighborhood interactions and impose a prior on smooth ground and class continuity. These Markov random fields interact through a hidden semi-Markov model that enforces a prior on the vertical structure of elements in the environment. The system runs in real-time and has been trained and tested using real data from an agricultural setting. Results show that exploiting the 3D structure inherent in outdoor domains significantly improves ground height estimates and obstacle detection accuracy.
We have developed the CHIMP (CMU Highly Intelligent Mobile Platform) robot as a platform for executing complex tasks in dangerous, degraded, human‐engineered environments. CHIMP has a near‐human form factor, work‐envelope, strength, and dexterity to work effectively in these environments. It avoids the need for complex control by maintaining static rather than dynamic stability. Utilizing various sensors embedded in the robot's head, CHIMP generates full three‐dimensional representations of its environment and transmits these models to a human operator to achieve latency‐free situational awareness. This awareness is used to visualize the robot within its environment and preview candidate free‐space motions. Operators using CHIMP are able to select between task, workspace, and joint space control modes to trade between speed and generality. Thus, they are able to perform remote tasks quickly, confidently, and reliably, due to the overall design of the robot and software. CHIMP's hardware was designed, built, and tested over 15 months leading up to the DARPA Robotics Challenge. The software was developed in parallel using surrogate hardware and simulation tools. Over a six‐week span prior to the DRC Trials, the software was ported to the robot, the system was debugged, and the tasks were practiced continuously. Given the aggressive schedule leading to the DRC Trials, development of CHIMP focused primarily on manipulation tasks. Nonetheless, our team finished 3rd out of 16. With an upcoming year to develop new software for CHIMP, we look forward to improving the robot's capability and increasing its speed to compete in the DRC Finals.
Abstract-Autonomous navigation in vegetation is challenging because the vegetation often hides the load-bearing surface which is used for evaluating the safety of potential actions. It is difficult to design rules for finding the true ground height in vegetation from forward looking sensor data, so we use an online adaptive method to automatically learn this mapping through experience with the world. This approach has been implemented on an autonomous tractor and has been tested in a farm setting. We describe the system and provide examples of finding obstacles and improving roll predictions in the presence of vegetation. We also show that the system can adapt to new vegetation conditions. I. INTRODUCTION AND RELATED WORK Automated vehicles that can safely operate in rough terrain would benefit many applications in agriculture, mining, and the exploration of hazardous areas. Operating in the unstructured environments common in these applications requires a vehicle to recognize untraversable areas and terrain interactions that could cause damage to the vehicle. This is a challenging task due to the complex interactions between the vehicle and the terrain, an environment that is often unknown or changing, and the limitations of current sensing technologies to provide measurements of important quantities, such as the the load-bearing surface of the upcoming terrain.Vegetation further complicates the situation by covering and hiding the load-bearing surface, preventing a purely geometric interpretation of the world. In many agricultural applications, the vehicle is required to drive through vegetation, and in more general off-road exploration tasks, driving through vegetated areas may save time or provide the only possible route to a goal. Vegetation also changes based on the season and weather.Many researchers have approached the rough terrain navigation problem by creating terrain representations from sensor information and then using a vehicle model to make predictions of the future vehicle trajectory to determine safe control actions [1], [2], [3], [4]. These techniques have been successful on rolling terrain with discrete obstacles and have shown promise in more cluttered environments, but handling vegetation remains a challenging problem.Navigation in vegetation is difficult because the range points from forward looking sensors such as stereo cameras or a laser range-finder do not generally give the load-bearing surface. Classification of vegetation and solid substances [5] can be useful for this task, but it is not sufficient. A grassy area on a
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.