United States

Interpreting spatial language not only adds a perceptual modality for robots, but also reduces the barrier of interfacing with humans. However, spatial language is inherently subjective and ambiguous. We thus consider spatial language as stochastic observations. We propose SLOOP (Spatial Language Object-Oriented POMDP), a new framework for partially observable decision making with a probabilistic observation model for spatial language, and apply it to object search in city-scale environments. Results demonstrate successful leverage of spatial language for faster target search.

IEEE RO-MAN 2021

Spatial Language Understanding for Object Search in Partially Observed City-scale Environments

object search

spatial language

pomdp

ECAI2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI, including:




**An extensive programme of workshops, tutorials, and invited speakers**

**The Prestigious Applications of Intelligent Systems conference (PAIS)**

**The Frontiers in AI track sessions**

**The Lab To Market event**

**The Women in AI time**

**The EU Challenges forum**

… and many more!

ECAI 2020

ECAI 2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI.

panel

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. 

We present a visual perception system for social robots
that is able to detect a person’s engagement in an interaction
from nonverbal cues independently of principal user activity.
This was achieved by the introduction of a set of proxemics,
body posture and attention features extracted with a Kinect sensor.
The system simultaneously classifies if a person is attempting to interact with the camera and regresses the user's level of availability. Finally, a prototype was implemented which is able to run both previous estimates in real-time using a shared feature vector.

PredGaze:A Incongruity Prediction Model for User’s Gaze Movement

A novel Synthesized Trust Learning (STL) method was developed to model human trust in the collaboration. STL explored using heterogeneous human feedback to model human trust. Specifically, human operator’s trust level and trust preference.

A Laser Projection System for

To build an agent providing assistance to human rescuers in an urban search and rescue task, it is crucial to predict their strategies. Developing data-driven models to predict them requires costly data collection and training for each new environment. We investigate transfer learning to mitigate this challenge (a) from a source environment with smaller number of types of injured victims to one with more types and (b) from a simpler environment to a more complex one for navigation strategy.

A Layered Control Approach to Human-Aware Task and Motion

Illusory Control that we proposed is a new teleoperation method that aims to increase the sensory value of comfort and happiness in teleoperation of mobile robots by providing visual feedback that seems to trick the operator. By conducting subject experiments, we compared the proposed method with conventional teleoperation methods such as direct teleoperation and shared control, and showed the possibility of improving task efficiency and system acceptance.

Teleoperation Method by Illusion of Human Intention and Time

In virtual reality, analogously, we can be a super-powered virtual giant who can supervise a swarm of robots in a vast and remote environment by flying over or resizing the world, and coordinate them by picking and placing a robot or creating virtual walls. This work implements this idea by using Virtual Reality along with Leap Motion, which is then validated by proof-of-concept experiments using real and virtual mobile robots in mixed reality.

Development of a Shared Indoor Smart Mobility Platform Based on Semi-Autonomous Driving

This work builds a dual-master/dual-slave teleoperation system that includes comprehensive force feedback on both arms and fingers. The system greatly improves the teleoperation experience, and some demonstrations on daily tasks are presented. Besides, this paper proposes a unified control architecture for the teleoperation scenario. This modular architecture design greatly facilitates research exploration in the teleoperation system.

Recurrent Neural Networks for Inferring Intentions in Shared Tasks for Industrial Collaborative Robots

We developed a high-level decision-making subsystem, a model-based context classifier, and a multi-objective optimization-based local planner to achieve socially-aware trajectories for autonomously sensed contexts. Using a context classification system, the robot can select social objectives that are later used by Pareto Concavity Elimination Transformation (PaCcET) based local planner to generate safe, comfortable, and socially appropriate trajectories for its environment. This was tested and validated in multiple environments on a Pioneer mobile robot platform.

DroneLight: Drone Draws in the Air using Long Exposure Light Painting and ML

Based on a user-study with experts in motion planning algorithms, we propose a taxonomy of explanations, including kinds of questions/explanations/methods related to motion planning, and a set of design considerations for explainable motion planning.

How experts explain motion planner output: a preliminary user-study to inform the design of explainable planners

We propose adding null-space motion to an online MPC-generated trajectory reference to avoid joint stiction and thus facilitate kinesthetic teaching in a redundant robot. Consequently, a reduction of the friction torque dispersion has been experimentally observed with this method. The trajectory deviations observed when adding null-space motion have been corrected experimentally by performing a fast sampling of the manipulator’s Jacobian matrix and by using angular joint position sensor feedback for the online reference trajectory recalculation.

Meet Your Personal Cobot but don‘t touch it just yet!

Interactive Task Learning is a research approach that studies the design of intelligent agents that can acquire knowledge from human instruction. This research has largely been robot-centered. We study this problem from a human-centered perspective. We conduct an interactive teaching study (N=10), and conduct a cognitive task analysis to characterize various aspects of teaching actions executed in natural human teaching. We propose ITL robot design recommendations using a computational theory SharedPlans that can support different participant teaching styles.

Premium content

Spatial Language Understanding for Object Search in Partially Observed City-scale Environments

Downloads

Next from IEEE RO-MAN 2021

PredGaze:A Incongruity Prediction Model for User’s Gaze Movement

Similar lecture

Monte Carlo Information-Oriented Planning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES