Achievable safety of driverless ground vehicles

Kim

International Journal of Human-Computer Interaction

et al. 2015

171

Although automation technology is increasingly replacing human to perform complex tasks such as driving, eliminating human intervention from driving may imply significant safety and trustrelated concerns. To address this issue from a psychological perspective, this study applies layers of anthropomorphic cues to an artificial driving agent to promote positive perceptions of an unmanned driving system. In a between-subjects factorial experiment (N = 89), participants interacted with an artificial driving agent with different levels of anthropomorphism induced by the variations in appearance (human-like vs. gadget-like) and autonomy (high vs. low) of the agent. The results indicated that an agent with human-like appearance and high autonomy were more effective in eliciting positive perceptions of the agent, which in turn the external (i.e., appearance) and internal (i.e., autonomy) anthropomorphic cues can be both strategically manipulated to demonstrate the feasibility of psychologically increasing the safety and trustworthiness of autonomous vehicles. In addition, a mediation analysis revealed that the role of social presence, suggesting that perceiving the driving agent as intelligent, safe, and trustworthy is largely determined by the feelings of social presence experienced during their interaction.

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Can Autonomous Vehicles Be Safe and Trustworthy? Effects of Appearance and Autonomy of Unmanned Driving Systems

Kim

International Journal of Human-Computer Interaction

et al. 2015

171

Road Vehicle Automation

“…In robotics, a state where all possible movement result in a crash is referred to as an inevitable collision state [3]. Researchers have acknowledged that with road vehicles, there is no way to completely avoid inevitable collision states [4], only to minimize the probability of entering one [5]. The only reasonable strategy is to construct a model of the expected behavior of nearby vehicles and try to avoid likely collisions-based on patent filings, this appears to be a component of Google's self-driving car [6].…”

Section: mentioning

confidence: 99%

Machine Ethics and Automated Vehicles

Goodall

2014

143

Road vehicle travel at a reasonable speed involves some risk, even when using computer-controlled driving with failure-free hardware and perfect sensing. A fully-automated vehicle must continuously decide how to allocate this risk without a human driver's oversight. These are ethical decisions, particularly in instances where an automated vehicle cannot avoid crashing. In this chapter, I introduce the concept of moral behavior for an automated vehicle, argue the need for research in this area through responses to anticipated critiques, and discuss relevant applications from machine ethics and moral modeling research. Ethical Decision Making for Automated VehiclesVehicle automation has progressed rapidly this millennium, mirroring improvements in machine learning, sensing, and processing. Media coverage often focuses on the anticipated safety benefits from automation, as computers are expected to be more attentive, precise, and predictable than human drivers. Mentioned less often are the novel problems from automated vehicle crash. The first problem is liability, as it is currently unclear who would be at fault if a vehicle crashed while self-driving. The second problem is the ability of an automated vehicle to make ethically-complex decisions when driving, particularly prior to a crash. This chapter focuses on the second problem, and the application of machine ethics to vehicle automation. Driving at any significant speed can never be completely safe. A loaded tractor trailer at 100 km/hr requires eight seconds to come to a complete stop, and a passenger car requires three seconds [1]. Truly safe travel requires accurate predictions of other vehicle behavior over this time frame, something that is simply not possible given the close proximities of road vehicles.To ensure its own safety, an automated vehicle must continually assess risk: the risk of traveling a certain speed on a certain curve, of crossing the centerline to

2018 21st International Conference on Intelligent Transportation Systems (ITSC)

“…Thornton et al present a motion planning framework based on Model Predictive Control [10]. In contrast to [7], constraints are explicitly formulated as hard and soft constraints. This comprises the need for collision-free trajectories (hard constraints) as well as ethical considerations and traffic rules (soft constraints).…”

Section: Related Workmentioning

confidence: 99%

Representing the Unknown – Impact of Uncertainty on the Interaction between Decision Making and Trajectory Generation

Nolte

Ernst

Richelmann

et al. 2018

Even though motion planning for automated vehicles has been extensively discussed for more than two decades, it is still a highly active field of research with a variety of different approaches having been published in the recent years. When considering the market introduction of SAE Level 3+ vehicles, the topic of motion planning will most likely be subject to even more detailed discussions between safety and user acceptance. This paper shall discuss parameters of the motion planning problem and requirements to an environment model. The focus is put on the representation of different types of uncertainty at the example of sensor occlusion, arguing the importance of a well-defined interface between decision making and trajectory generation.