Sanne van Waveren

I am a PhD student at KTH Royal Institute of Technology.

My vision is a future of safe, robust, and verifiable robots that leverage human feedback to automatically synthesize correct behaviors that are perceived acceptable.

I enable robots to recover from real-world failures, so they can continue their tasks even after their policy or plan failed.

My research leverages non-expert feedback for the application of formal methods to computational human-robot interaction, with the aim of developing new ways to automatize robot failure corrections.

For an up-to-date list of my papers see my publications page.

news

Dec 22, 2021	Paper Accepted into HRI22: Correct Me If I'm Wrong: Using Non-Experts to Repair Reinforcement Learning Policies Read more
Dec 20, 2021	I was selected to participate in HRI Pioneers 2022. Looking forward to present and discuss my work on leveraging non-Experts and formal Methods to automatically correct robot failures and meet this year’s cohort! Read more about HRI Pioneers
Oct 22, 2021	I started a research visit in the Robotics Institute at CMU with Liz Carter.
Jul 29, 2021	Paper accepted into Frontiers in Robotics and AI Read more
Mar 17, 2021	Paper Accepted PERSUASIVE 2021: Breaking the Taboo: Using a Social Robot to Raise Women’s Awareness of Menstrual Health Read more
Mar 5, 2021	Paper Accepted ICRA 2021: Encoding Human Driving Styles in Motion Planning for Autonomous Vehicles Read more
Oct 29, 2020	Gesticulator wins best paper at ICMI20. Big congrats to first and second author, Taras and Patrik, for leading this work.
Aug 7, 2020	Paper Accepted at ICMI20: Gesticulator: A framework for semantically-aware speech-driven gesture generation Read more
Nov 30, 2019	Paper Accepted to HRI20. Behavioural Responses to Robot Conversational Failures Read more
Nov 30, 2019	Paper Accepted into CHI20: Embodiment Effects in Interactions with Failing Robots Read more
Aug 14, 2019	Paper Accepted into ICSR19: Knock on Wood: The Effects of Material Choice on the Perception of Social Robots Read more
Apr 10, 2019	Paper Accepted into IVA2019: Take One For the Team: The Effects of Error Severity in Collaborative Tasks with Social Robots Read more
Nov 30, 2018	Paper Accepted into HRI19: Comparing Human-Robot Proxemics Between Virtual Reality and the Real World Read more

selected publications

Encoding Human Driving Styles in Motion Planning for Autonomous Vehicles

Karlsson, Jesper*, van Waveren*, Sanne, Pek, Christian, Torre, Ilaria, Leite, Iolanda, and Tumova, Jana

In ICRA International Conference on Robotics and Automation 2021

Abs HTML Video

Driving styles play a major role in the acceptance and use of autonomous vehicles. Yet, existing motion planning techniques can often only incorporate simple driving styles that are modeled by the developers of the planner and not tailored to the passenger. We present a new approach to encode human driving styles through the use of signal temporal logic and its robustness metrics. Specifically, we use a penalty structure that can be used in many motion planning frameworks, and calibrate its parameters to model different automated driving styles. We combine this penalty structure with a set of signal temporal logic formula, based on the Responsibility-Sensitive Safety model, to generate trajectories that we expected to correlate with three different driving styles: aggressive, neutral, and defensive. An online study showed that people perceived different parameterizations of the motion planner as unique driving styles, and that most people tend to prefer a more defensive automated driving style, which correlated to their self-reported driving style.
Gesticulator: A framework for semantically-aware speech-driven gesture generation

Kucherenko, Taras, Jonell, Patrik, van Waveren, Sanne, Henter, Gustav Eje, Alexandersson, Simon, Leite, Iolanda, and Kjellström, Hedvig

In Proceedings of the 2020 International Conference on Multimodal Interaction 2020

Abs HTML Code

During speech, people spontaneously gesticulate, which plays a key role in conveying information. Similarly, realistic co-speech gestures are crucial to enable natural and smooth interactions with social agents. Current data-driven co-speech gesture generation systems use a single modality for representing speech: either audio or text. These systems are therefore confined to producing either acoustically-linked beat gestures or semantically-linked gesticulation (e.g., raising a hand when saying “high”): they cannot appropriately learn to generate both gesture types. We present a model designed to produce arbitrary beat and semantic gestures together. Our deep-learning based model takes both acoustic and semantic representations of speech as input, and generates gestures as a sequence of joint angle rotations as output. The resulting gestures can be applied to both virtual agents and humanoid robots. Subjective and objective evaluations confirm the success of our approach.
Behavioural responses to robot conversational failures

Kontogiorgos, Dimosthenis, Pereira, Andre, Sahindal, Boran, van Waveren, Sanne, and Gustafson, Joakim

In Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction 2020

Abs HTML

Humans and robots will increasingly collaborate in domestic environments which will cause users to encounter more failures in interactions. Robots should be able to infer conversational failures by detecting human users’ behavioural and social signals. In this paper, we study and analyse these behavioural cues in response to robot conversational failures. Using a guided task corpus, where robot embodiment and time pressure are manipulated, we ask human annotators to estimate whether user affective states differ during various types of robot failures. We also train a random forest classifier to detect whether a robot failure has occurred and compare results to human annotator benchmarks. Our findings show that human-like robots augment users’ reactions to failures, as shown in users’ visual attention, in comparison to non-human-like smart-speaker embodiments. The results further suggest that speech behaviours are utilised more in responses to failures when non-human-like designs are present. This is particularly important to robot failure detection mechanisms that may need to consider the robot’s physical design in its failure detection model.