Sanne van Waveren

selected publications

1. 

   Correct Me If I’m Wrong: Using Non-Experts to Repair Reinforcement Learning Policies

   Van Waveren, Sanne, Pek, Christian, Tumova, Jana, and Leite, Iolanda

   In Proceedings of the 17th ACM/IEEE International Conference on Human-Robot Interaction 2022

   Abs Bib HTML

   Reinforcement learning has shown great potential for learning sequential decision-making tasks. Yet, it is difficult to anticipate all possible real-world scenarios during training, causing robots to inevitably fail in the long run. Many of these failures are due to variations in the robot’s environment. Usually experts are called to correct the robot’s behavior; however, some of these failures do not necessarily require an expert to solve them. In this work, we query non-experts online for help and explore 1) if/how non-experts can provide feedback to the robot after a failure and 2) how the robot can use this feedback to avoid such failures in the future by generating shields that restrict or correct its high-level actions. We demonstrate our approach on common daily scenarios of a simulated kitchen robot. The results indicate that non-experts can indeed understand and repair robot failures. Our generated shields accelerate learning and improve data-efficiency during retraining.

   @inproceedings{van2022correct,
     title = {Correct Me If I'm Wrong: Using Non-Experts to Repair Reinforcement Learning Policies},
     author = {Van Waveren, Sanne and Pek, Christian and Tumova, Jana and Leite, Iolanda},
     booktitle = {Proceedings of the 17th ACM/IEEE International Conference on Human-Robot Interaction},
     pages = {1--9},
     year = {2022},
     html = {https://sannevw.github.io/assets/pdf/vanWaveren_Hri2022_Final_PP.pdf},
     selected = {true}
   }

2. 

   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 Bib 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.

   @inproceedings{karlsson2021encoding,
     title = {Encoding Human Driving Styles in Motion Planning for Autonomous Vehicles},
     author = {Karlsson, Jesper* and {van Waveren}*, Sanne and Pek, Christian and Torre, Ilaria and Leite, Iolanda and Tumova, Jana},
     booktitle = {ICRA International Conference on Robotics and Automation},
     year = {2021},
     selected = {true},
     html = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9561777},
     video = {https://youtu.be/z5IXIdPKX_o}
   }

3. 

   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 Bib 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.

   @inproceedings{kucherenko2020gesticulator,
     title = {Gesticulator: A framework for semantically-aware speech-driven gesture generation},
     author = {Kucherenko, Taras and Jonell, Patrik and {van Waveren}, Sanne and Henter, Gustav Eje and Alexandersson, Simon and Leite, Iolanda and Kjellstr{\"o}m, Hedvig},
     booktitle = {Proceedings of the 2020 International Conference on Multimodal Interaction},
     pages = {242--250},
     year = {2020},
     selected = {true},
     html = {https://svito-zar.github.io/papers/Gesticulator_ICMI_2020.pdf},
     code = {https://github.com/Svito-zar/gesticulator},
     award = {Best paper award}
   }

4. 

   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 Bib 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.

   @inproceedings{kontogiorgos2020behavioural,
     title = {Behavioural responses to robot conversational failures},
     author = {Kontogiorgos, Dimosthenis and Pereira, Andre and Sahindal, Boran and {van Waveren}, Sanne and Gustafson, Joakim},
     booktitle = {Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction},
     pages = {53--62},
     year = {2020},
     selected = {true},
     html = {https://dl.acm.org/doi/pdf/10.1145/3319502.337478}
   }