From the Moon to the Earth: Planetary Exploration to Self-Driving Cars
This presentation provides an overview of robotics research activities at NASA Ames, which range from new techniques for planetary exploration to self-driving cars.
Fong, Terry↗
SEARCH · Search NASA
Results for “self driving”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Our Home with the Robots: From Planetary Rovers to Self-Driving Cars
Presents high-level overview of research at NASA Ames on human-robot teaming, ranging from crew-controlled surface telerobotics to remote assistance for self-driving cars.
Fong, Terry↗
Human-Robot Teaming: From Space Robotics to Self-Driving Cars
In this talk, I describe how NASA Ames has been developing and testing robots for space exploration. In our research, we have focused on studying how human-robot teams can increase the performance, reduce the cost, and increase the success of space missions. A key tenet of our work is that humans and robots should support one another in order to compensate for limitations of manual control and autonomy. This principle has broad applicability beyond space exploration. Thus, I will conclude by discussing how we have worked with Nissan to apply our methods to self-driving cars, enabling humans to support autonomous vehicles operating in unpredictable and difficult situations.
robotics↗
Human-Robot Teaming: From Space Robots to Self-Driving Cars
This presentation describes various factors that are pertinent to human-robot teaming and then summarizes relevant research performed at NASA Ames.
Fong, Terry↗
Human-Robot Teaming: From Space Robotics to Self-Driving Cars
Overview of human-robot teaming research at NASA Ames, which includes work on communication, coordination, and collaboration.
Fong, Terry↗
Is "Sleepy Supervision" the New "Drowsy Driving"?
Human error has been implicated as a causal factor in a large proportion of road accidents. Automated driving systems purport to mitigate this risk, but self-driving systems that allow a driver to entirely disengage from the driving task also require the driver to monitor the environment and take control when necessary. Given that sleep loss impairs monitoring performance and there is a high prevalence of sleep deficiency in modern society, we hypothesized that supervising a self-driving vehicle would unmask latent sleepiness compared to manually controlled driving among individuals following their typical sleep schedules. We found that participants felt sleepier, had more involuntary transitions to sleep, had slower reaction times and more attentional failures, and showed substantial modifications in brain synchronization during and following an autonomous drive compared to a manually controlled drive. Our findings suggest that the introduction of partial self-driving capabilities in vehicles has the potential to paradoxically increase accident risk.
sleepiness↗
Synergies Between Assured Autonomy for Aviation and Automated Driving
Presentation offers methodology and approaches for increasing autonomy in aviation and uses car industry (self-driving cars) as comparison.
Aviation↗
Telerobotic Perception During Asteroid and Mars Regolith Operations Project
Current space telerobotic systems are constrained to only operating in bright light and dust-free conditions. This project will study the effects of difficult lighting and dust conditions on telerobotic perception systems to better assess and refine regolith operations on other neighboring celestial bodies. In partnership with Embry-Riddle Aeronautical University and Caterpillar, Inc., optical, LiDAR and RADAR sensing equipment will be used in performing the study. This project will create a known dust environment in the Swamp Works Granular Mechanics & Regolith Operations (GMRO) Laboratory regolith test bin to characterize the behavior of the sensing equipment in various calibrated lighting and dust conditions. It will also identify potential methods for mitigating the impacts of these undesirable conditions on the performance of the sensing equipment. Enhancing the capability of telerobotic perception systems will help improve life on earth for those working in dangerous, dusty mining conditions, as well as help advance the same technologies used for safer self-driving automobiles in various lighting and weather conditions. It will also prove to be a critical skill needed for advancing robotic and human exploration throughout our solar system, for activities such as mining on an asteroid or pioneering the first colony on Mars.
Technology Portfolio System↗
How NASA's Technology Can Help the Automotive Industry
Presentation describes how automobile companies developing self-driving cars and NASA face similar challenges which can be solved using similar technologies. To provide context, the presentation also describes how NASA Ames is working with automobile companies, such as Nissan, to research and development relevant technologies.
autonomy↗
Transformational Autonomy and Personal Transportation: Synergies and Differences Between Cars and Planes
Highly automated cars have undergone tremendous investment and progress over the past ten years with speculation about fully-driverless cars within the foreseeable, or even near future, becoming common. If a driverless future is realized, what might be the impact on personal aviation? Would self-piloting airplanes be a relatively simple spin-off, possibly making travel by personal aircraft also commonplace? What if the technology for completely removing human drivers turns out to be further in the future rather than sooner; would such a delay suggest that transformational personal aviation is also somewhere over the horizon or can transformation be achieved with less than full automation? This paper presents a preliminary exploration of these questions by comparing the operational, functional, and implementation requirements and constraints of cars and small aircraft for on-demand mobility. In general, we predict that the mission management and perception requirements of self-piloting aircraft differ significantly from self-driving cars and requires the development of aviation specific technologies. We also predict that the highly-reliable control and system automation technology developed for conditionally and highly automated cars can have a significant beneficial effect on personal aviation, even if full automation is not immediately feasible.
Goodrich, Kenneth H.↗
Safe and Autonomous Drones for Urban Flight
Autonomous vehicles are no longer futuristic technology; in fact, there are already cars with self-driving features on the road. Over the next five years, the connected vehicles will disrupt the entire automotive and UAS ecosystems. The industry will undergo fundamental change as semi-autonomous driving and flying emerges, followed by an eventual shift to full autonomy.
Safety↗
Human-Robot Teaming: Communication, Coordination, and Collaboration
In this talk, I will describe how NASA Ames has been studying how human-robot teams can increase the performance, reduce the cost, and increase the success of a variety of endeavors. The central premise of our work is that humans and robots should support one another in order to compensate for limitations of automation and manual control. This principle has broad applicability to a wide range of domains, environments, and situations. At the same time, however, effective human-robot teaming requires communication, coordination, and collaboration -- all of which present significant research challenges. I will discuss some of the ways that NASA Ames is addressing these challenges and present examples of our work involving planetary rovers, free-flying robots, and self-driving cars.
robotics↗
2018 Workshop on Autonomy for Future NASA Science Missions
Autonomy is changing our world; commercial enterprises and academic institutions are developing and deploying drones, robots, self-driving vehicles and other autonomous capabilities to great effect here on Earth. Autonomous technologies will also play a critical and enabling role in future NASA science missions, and the Agency requires a specific strategy to leverage these advances and infuse them into its missions. To address this need, NASA sponsored the 2018 Workshop on Autonomy for NASA Science Missions, held at Carnegie Mellon University, October 10-11, 2018.
Florence W Tan↗
Thinking outside the box: The human role in increasingly automated aviation systems
Rapid advances in artificial intelligence are enabling automated systems to operate in an increasingly autonomous manner in domains that previously required the involvement of human operators. Examples are rail transport systems, self-driving cars, and warehouse delivery systems. From time to time, such automation encounters operational conditions that fall outside a “competency box” within which the system has been designed to operate. Human operators add resilience because they can see and act outside the competency box of scenarios and environments for which the system was designed. The system’s competencies can be expanded over time with modifications to software, sensors, etc.; however, it is unclear at what point the competency box becomes large enough to safely eliminate the role of the human operator. One area where advanced automation may be applied is Urban Air Mobility (UAM). Current UAM concepts envision fleets of highly automated air vehicles providing on-demand transport for people and goods. A phased development of UAM has been proposed, beginning with on-board pilots and transitioning to a future state where automated vehicles operate with minimal human involvement. Proponents of UAM note that this final state reduces cost as well as eliminating pilot error, identified as a contributing factor in many aircraft accidents. However, eliminating human involvement also risks eliminating their positive contributions to system resilience. Here we examine Concepts of Operation proposed for future UAM systems and explore how humans can best be incorporated to maintain resilience while minimizing cost and risk. A human-autonomy teaming approach is suggested.
Advanced Air Mobility↗
High-capacity ATHLETE Offloader Mobility Constructor Concept for Human Surface Exploration
Using cross-cabled, winch-tendon four-bar frames, a new Artemis-class ATHLETE system is a multi-limbed robotic mobility platform that is designed for surface traverse, precision placement, and offloading of heavy habitats and other large human exploration payloads from high-decked landers. Building upon lessons learned from the All-Terrain Hex-Limbed Extra-Terrestrial Explorer (ATHLETE) robotic mobility system developed for Constellation Lunar Surface Systems and Evolvable Mars Campaign, a high-capacity articulated crane / lift vehicle concept has been devised that would be equipped with multi-limb six-degree-of-freedom dexterity for a variety of tasks supporting planetary surface human exploration missions and outposts. The Artemis-class ATHLETE vehicle would use any combination of three to six wheel-onlimb combinations to provide a wide “outrigger” stance to transfer loads from a high center-of-gravity on sloped terrain to low stable carry configurations for long-distance traverses, and be capable of precision docking of payloads to previously positioned elements. The new vehicle concept improves upon previous Constellation-class ATHLETE versions by allowing modular hot-swapping of individual limbs to improve maintenance and flexibility. The extreme-capacity independent limbs can individually function as single cranes, and can be delivered separately via multiple lander manifests for later congregation into self-driving “Tri-ATHLETE” vehicles after delivery to the surface. This paper provides mission architecture targets and vehicle masses for stepped payload capacity values in Earth, Mars, and Lunar gravity environments, and discusses a variety of swappable tools, including wheeled mobility attachments, grippers, excavation tools, repair fixtures, ISRU extraction, winches, block & tackle rigging combinations, 3D printheads, and construction aids.
Wilcox, Brian↗
Robotics Technology: From Space Exploration to Autonomous Vehicles
Briefing on the parallels between space exploration (planetary rovers) and autonomous vehicles (self-driving cars)
autonomous vehicles↗
AI4MARS: A Dataset for Terrain-Aware Autonomy on Mars
Deep learning has quickly become a necessity for selfdriving vehicles on Earth. In contrast, the self-driving vehicles on Mars, including NASA’s latest rover, Perseverance, which is planned to land on Mars in February 2021, are still driven by classical machine vision systems. Deep learning capabilities, such as semantic segmentation and object recognition, would substantially benefit the safety and productivity of ongoing and future missions to the red planet. To this end, we created the first large-scale dataset, AI4Mars, for training and validating terrain classification models for Mars, consisting of ~326K semantic segmentation full image labels on 35K images from Curiosity, Opportunity, and Spirit rovers, collected through crowdsourcing. Each image was labeled by ~10 people to ensure greater quality and agreement of the crowdsourced labels. It also includes ~1.5K validation labels annotated by the rover planners and scientists from NASA’s MSL (Mars Science Laboratory) mission, which operates the Curiosity rover, and MER (Mars Exploration Rovers) mission, which operated the Spirit and Opportunity rovers. We trained a DeepLabv3 model on the AI4Mars training dataset and achieved over 96% overall classification accuracy on the test set. The dataset is made publicly available.1
Ono, Hiro↗
Data-Centric Operational Design Domain Characterization for Machine Learning-Based Aeronautical Products
We give for Machine Learning (ML)-based aeronautical products, a first rigorous characterization of Operational Design Domains (ODDs). Unlike in other application sectors (such as self-driving road vehicles) where ODD development is scenario-based, our approach is data-centric: we propose the dimensions along which the parameters that define an ODD can be explicitly captured, using a top-down approach starting from system specifications, and a bottom-up approach starting from detailed ML Model (MLM) designs. Then we give a categorization of the data that ML-based applications can encounter in operation, identifying their system-level relevance and impact. Specifically, we discuss how those data categories are useful to determine: (1) the requirements necessary to drive the design of MLMs; (2) the potential effects on the MLM and higher levels of the system hierarchy; (3) the learning assurance processes that may be needed, and (4) system architectural considerations. We illustrate the underlying concepts with an example of an aircraft flight envelope. The approach in this paper is one of the cornerstones of a future process guidance for development and certification/approval of safety-related aeronautical products implementing Artificial Intelligence (AI), currently being developed through aviation industry-based consensus, jointly by the SAE G-34 Committee for AI in aviation, and EUROCAE WG-114 for AI.
Aeronautical products↗