United States

When developing AI systems that interact with humans, it is essential to design both a system that can understand humans, and a system that humans can understand. We develop a deep interpretable modular neural framework for modeling the intentions of other observed entities. We demonstrate the efficacy of our approach with experiments on data from human participants on a search and rescue task in Minecraft, and show that incorporating interpretability can significantly increase predictive performance under the right conditions.

IEEE RO-MAN 2021

Performing Human-Robot Interaction User Studies in Virtual Reality

social intelligence

theory of mind

interpretability

deep learning

RO-MAN 2021's theme is trustworthiness and cooperation. We chose this term well before the pandemic put the world on edge and added a new reason for us to question our own personal safety when in the company of others. But what about in the company of social robots? What would cause us to trust, or not trust, them? How do we as researchers create that feeling, that critical component of any relationship? With social robots, it is of course largely in our power to design the physical form, the control code and the interface software to maximize trustworthiness, facilitate cooperation and enhance the quality of human-robot interaction. This theme also touches upon people's expectations and perceptions of robots, as well as other social, cognitive and cultural factors that will influence human-robot interactions. We will have a special session/track on this topic, invite targeted submissions and include plenary speakers who are specialist in this area. We sincerely hope that this focus will help enlighten the design-thinking of all of us as we fabricate and program our own various systems.

To access RO-MAN Virtual 2021, [please register here.](https://ro-man2021.org/registration/)

RO-MAN 2021's theme is trustworthiness and cooperation. We chose this term well before the pandemic put the world on edge and added a new reason for us to question our own personal safety when in the company of others. But what about in the company of social robots? What would cause us to trust, or not trust, them? How do we as researchers create that feeling, that critical component of any relationship? With social robots, it is of course largely in our power to design the physical form, the control code and the interface software to maximize trustworthiness, facilitate cooperation and enhance the quality of human-robot interaction. 

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


ICPR 2020

panel

The paper describes the Nao_PRM application aimed at expanding the limited functionality of the simulated Nao robot, already integrated into the Choregraphe application, creating a robot simulation with all the required functionalities for social interaction.

Efficient, Situated and Ontology based Referring Expression Generation for Human-Robot collaboration

This project relates to developing a framework for physiologically adaptive robotic scenarios. By exploring the designs of previously developed systems, we can better provide a general structure and multi-purpose tools to help facilitate the integration of physiological signals into HRI applications.

Hand-Motion-guided Articulation and Segmentation Estimation

Studies have shown that the appearance and movements of home robots may play key roles in the impression and engagement of users, opposed to recent rises in the smart speaker market. In this research, we conduct a user experiment with the aim of clarifying the elements required to evaluate the human impression of a robot's movements, based on the hypothesis that adequate movements may lead to better impressions and engagement.

Impression Evaluation of Robots Behavior When Assisting Human in a Cooking Task

We explored using human cognitive traits as predictive measures for human-robot team task performance. We developed several tests that quantify human cognitive traits, and analyzed the relationships between the test scores and performances on several human-robot team tasks.

Predicting Individual Human Performance in Human-Robot Teaming

We developed a new rule-based dialog system, which appropriately switches responses without interfering with human speech. The traditional rule-based part allows the system user to design and customize topics and conversation transitions easily. However, the system’s speech sometimes superimposes on human’s speech. To solve this problem, we installed turn-taking detection, which can detect the human speaker’s continuous speech, and a function to select response by using detection results. Practical experiment suggested that our system may enable smooth conversations.

Increasing Engagement with Chameleon Robots in Bartending Services

We introduce a Grasp Manifold Estimator (GraspME) to find object's grasp affordances directly in camera images. Predicting grasp manifolds has the advantage of generalizing to continuously infinitely many grasps, which is not the case when using other grasp representations. We approximate grasp manifolds via a set of keypoints and locate them in images using Mask R-CNN as a backbone. We rely on simulation data only and perform experiments on simple and complex objects, including unseen ones and real data.

GraspME - Grasp Manifold Estimator

We propose a learning system in which language is grounded in visual percepts without specific pre-defined categories of terms. We present a unified generative method to acquire a shared semantic/visual embedding that enables the learning of language about a wide range of real-world objects. We evaluate the efficacy of this learning by predicting the semantics of objects and comparing the performance with neural and non-neural inputs. We show that this generative approach exhibits promising results in language grounding without pre-specifying visual categories under low resource settings. Our experiments demonstrate that this approach is generalizable to multilingual, highly varied datasets.

Neural Variational Learning for Grounded Language Acquisition

Data-driven approaches for modeling human skeletal motion have found various applications in interactive media and social robotics. Challenges remain in these fields for generating high-fidelity samples and robustly reconstructing motion from imperfect input data, due to e.g. missed marker detection. In this paper, we propose a probabilistic generative model to synthesize and reconstruct long horizon motion sequences conditioned on past information and control signals, such as the path along which an individual is moving. Our method adapts the existing work MoGlow by introducing a new graph-based model. The model leverages the spatial-temporal graph convolutional network (ST-GCN) to effectively capture the spatial structure and temporal correlation of skeletal motion data at multiple scales. We evaluate the models on a mixture of motion capture datasets of human locomotion with foot-step and bone-length analysis. The results demonstrate the advantages of our model in reconstructing missing markers and achieving comparable results on generating realistic future poses. When the inputs are imperfect, our model shows improvements in the robustness of generation.

Defining Fairness in Human-Robot Teams

We propose a reinforcement learning model for the physical human–robot interaction. Our model estimates the opponent’s changing policy using variational autoencoder and expresses the agent’s policy in a common latent space. We verified the performance of the model using two novel physical and competitive environments, push-hand game and air-hockey in the simulator. The latent space worked properly as policy information of the agent’s own policy and that of the opponent.

Competitive Physical Interaction by Reinforcement Learning Agents Using Intention Estimation

The use of robotics in assisting humans and performingseveral different tasks is changing our lives. Unfortunately,for the execution of each new task, a time-consuming re-programming of the robot is necessary. This approach limitsthe adaptability of robots to new conditions. Ideally, robotsshould quickly adapt to unknown situations and learn directlyfrom experience or human demonstrations. What if even achild could teach a robot to drive autonomously?

Performing Human-Robot Interaction User Studies in Virtual Reality

Downloads

Next from IEEE RO-MAN 2021

Efficient, Situated and Ontology based Referring Expression Generation for Human-Robot collaboration

Similar lecture

Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES