This paper presents an autonomous driving test held in Parma on urban roads and freeways open to regular traffic. During this test, the vehicle not only performed simple maneuvers, but it had to cope with complex driving scenarios as well, including roundabouts, junctions, pedestrian crossings, freeway junctions, and traffic lights. The test demonstrated the ability of the current technology to manage real situations and not only the well-structured and predictable ones. A comparison of milestones, challenges, and key results in autonomous driving is presented to highlight the novelty and the specific purpose of the test. The whole system is described: the vehicle; the software architecture; details about high-, medium-, and low-level control; and details about perception algorithms. A conclusion highlights the achieved results and draws possible directions for future development.Alberto Broggi received the Dr.Ing. (master's) degree in electronic engineering and the Ph.D. degree in information technology both from the Università degli Studi di Parma, Parma, Italy, in 1990 and 1994, respectively. He is currently a Full Professor with the Università degli Studi di Parma, where he is also the President and CEO of the VisLab spinoff company. He is an author of more than 150 publications on international scientific journals, book chapters, and refereed conference proceedings. Dr. Broggi served as Editor-in-Chief of IEEE TRANSACTIONS ON IN-TELLIGENT TRANSPORTATION SYSTEMS for the term 2004-

An important topic in the autonomous driving research is the development of maneuver planning systems. Vehicles have to interact and negotiate with each other so that optimal choices, in terms of time and safety, are taken. For this purpose, we present a maneuver planning module able to negotiate the entering in busy roundabouts. The proposed module is based on a neural network trained to predict when and how entering the roundabout throughout the whole duration of the maneuver. Our model is trained with a novel implementation of A3C, which we will call Delayed A3C (D-A3C), in a synthetic environment where vehicles move in a realistic manner with interaction capabilities. In addition, the system is trained such that agents feature a unique tunable behavior, emulating real world scenarios where drivers have their own driving styles. Similarly, the maneuver can be performed using different aggressiveness levels, which is particularly useful to manage busy scenarios where conservative rule-based policies would result in undefined waits.

No abstract

A study was conducted to characterize the relationship between audio and video quality and the perceived quality of entertainment video services. A multiplicative model using perceived audio-only quality and video-only quality parameters was found to account for 98% of the variance in the mean opinion scores for overall audiohide0 quality. The unique feature of the model is that it predicts overall audiohide0 quality in terms of separate audio-only and videoonly perceived quality, rather than from separate audio-only and video-only impairment levels. Since the model is not defined in terms of specific impairments, but instead in terms of people's perception of quality, it is likely that the model will apply to other types of audio and video impairment combinations as well. This hypothesis has been supported by the results of subsequent research. The model may prove to be extremely valuable to system designers since it allows a costbenefit analysis of how changes in the relative quality of either the audio or video channel affect overall audiohide0 quality.

In the last few years, several philosophers have highlighted the social dimension of imagination. In this paper I argue that thought experiments prompt social uses of imaginings if we understand them as props in games of make-believe. In prescribing to imagine stories that develop through fictional narratives, authors of thought experiments prompt their readers to engage in the same imaginative project—at least in its salient aspects—and to endorse their conclusions. Contributions on this topic focus on cases where coordination across imaginers is immediately successful. However, this is not the end of the story. I draw attention to situations where this is not the case, as the practice of thought experimentation often proceeds through criticism, rejections, and amendments. I focus on cases where imaginers do not endorse the conclusion proposed by the author of a thought experiment and either (i) fully reject the principles of generation, (ii) draw different fictional truths from the same principles, or (iii) amend the principles. Although cases of imaginative disharmony are usually dismissed as failures, I acknowledge them as fruitful steps in the cognitive advancement achievable by thought experiments. Cooperative imaginers challenge the rules of the game in meaningful ways, which leads to enhancing fictional scenarios and framing them through different perspectives.