• Corpus ID: 208310222

Following Social Groups: Socially Compliant Autonomous Navigation in Dense Crowds

@article{Yao2019FollowingSG,
  title={Following Social Groups: Socially Compliant Autonomous Navigation in Dense Crowds},
  author={Xinjie Yao and Ji Zhang and Jean Oh},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.12063}
}
In densely populated environments, socially compliant navigation is critical for autonomous robots as driving close to people is unavoidable. This manner of social navigation is challenging given the constraints of human comfort and social rules. Traditional methods based on hand-craft cost functions to achieve this task have difficulties to operate in the complex real world. Other learning-based approaches fail to address the naturalness aspect from the perspective of collective formation… 

Figures and Tables from this paper

A Generative Approach for Socially Compliant Navigation

  • Chieh-En TsaiJean Oh
  • Computer Science
    2020 IEEE International Conference on Robotics and Automation (ICRA)
  • 2020
TLDR
NaviGAN is proposed, a generative navigation algorithm that jointly optimizes both of the comfort and naturalness aspects and is designed as an adversarial training framework that can learn to generate a navigation path that is both optimized for achieving a goal and for complying with latent social rules.

NaviGAN: A Generative Approach for Socially Compliant Navigation

TLDR
NaviGAN is proposed, a generative navigation algorithm that jointly optimizes both of thecomfort and naturalness aspects of socially compliant navigation and is designed as an adversarial training framework that can learn to generate a navigation path that is both optimized for achieving a goal and for complying with latent social rules.

Prevention and Resolution of Conflicts in Social Navigation - a Survey

TLDR
This survey starts by defining a conflict in social navigation, and offers a detailed taxonomy of its components, and maps existing work into this taxonomy, while discussing papers using its framing.

Evaluation of Socially-Aware Robot Navigation

TLDR
In this paper, the evaluation methods, scenarios, datasets, and metrics commonly used in previous socially-aware navigation research are reviewed, the limitations of existing evaluation protocols are discussed, and research opportunities for advancing social-aware robot navigation are highlighted.

Predicting Human Trajectories by Learning and Matching Patterns

TLDR
A Convolutional Neural Network-based approach to learn, detect, and extract patterns in sequential trajectory data, known here as Social Pattern Extraction Convolution (Social-PEC), which performs comparably to the state of the art and outperforms in some cases.

Motion planning and control for mobile robot navigation using machine learning: a survey

TLDR
This article surveys recent works that apply machine learning for motion planning and control in mobile robot navigation, within the context of classical navigation systems, to identify common challenges and promising future directions.

Motion Control for Mobile Robot Navigation Using Machine Learning: a Survey

TLDR
This article surveys recent works that apply machine learning for motion control in mobile robot navigation, within the context of classical navigation systems, and identifies common challenges and promising future directions.

Noticing Motion Patterns: A Temporal CNN With a Novel Convolution Operator for Human Trajectory Prediction

TLDR
A Convolutional Neural Network-based approach to learn, detect, and extract patterns in sequential trajectory data, known here as Social Pattern Extraction Convolution (Social-PEC), which performs comparably to the state of the art and outperforms in some cases.

MLNav: Learning to Safely Navigate on Martian Terrains

TLDR
Compared to the baseline ENav path planner on board the Perserverance rover, MLNav can provide a significant improvement in multiple key metrics, such as a 10x reduction in collision checks when navigating real Martian terrains, despite being trained with synthetic terrains.

Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation

TLDR
A new class of implicit control policies combining the benefits of imitation learning with the robust handling of system constraints from Model Predictive Control (MPC) are presented, called Performer-MPC, which achieves > 40% better goal reached in cluttered environments and > 65% better on social metrics when navigating around humans.

References

SHOWING 1-10 OF 15 REFERENCES

A Generative Approach for Socially Compliant Navigation

  • Chieh-En TsaiJean Oh
  • Computer Science
    2020 IEEE International Conference on Robotics and Automation (ICRA)
  • 2020
TLDR
NaviGAN is proposed, a generative navigation algorithm that jointly optimizes both of the comfort and naturalness aspects and is designed as an adversarial training framework that can learn to generate a navigation path that is both optimized for achieving a goal and for complying with latent social rules.

Crowd-Robot Interaction: Crowd-Aware Robot Navigation With Attention-Based Deep Reinforcement Learning

TLDR
This work proposes to rethink pairwise interactions with a self-attention mechanism, and jointly model Human-Robot as well as Human-Human interactions in the deep reinforcement learning framework, and captures the Human- human interactions occurring in dense crowds that indirectly affects the robot’s anticipation capability.

Socially aware motion planning with deep reinforcement learning

TLDR
Using deep reinforcement learning, this work develops a time-efficient navigation policy that respects common social norms and is shown to enable fully autonomous navigation of a robotic vehicle moving at human walking speed in an environment with many pedestrians.

Socially compliant mobile robot navigation via inverse reinforcement learning

TLDR
An extensive set of experiments suggests that the technique outperforms state-of-the-art methods to model the behavior of pedestrians, which also makes it applicable to fields such as behavioral science or computer graphics.

Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

TLDR
A recurrent sequence-to-sequence model observes motion histories and predicts future behavior, using a novel pooling mechanism to aggregate information across people, and outperforms prior work in terms of accuracy, variety, collision avoidance, and computational complexity.

Social LSTM: Human Trajectory Prediction in Crowded Spaces

TLDR
This work proposes an LSTM model which can learn general human movement and predict their future trajectories and outperforms state-of-the-art methods on some of these datasets.

The Walking Behaviour of Pedestrian Social Groups and Its Impact on Crowd Dynamics

TLDR
Analyzing the motion of approximately 1500 pedestrian groups under natural condition shows that social interactions among group members generate typical group walking patterns that influence crowd dynamics, demonstrating that crowd dynamics is not only determined by physical constraints induced by other pedestrians and the environment, but also significantly by communicative, social interaction among individuals.

Accompanying persons with a mobile robot using motion prediction and probabilistic roadmaps

TLDR
A local navigation planning approach for collision avoidance that uses probabilistic roadmaps to plan collision-free paths to a given target location relative to the robot and improves the performance of the collision avoidance and the robot's ability to stay close to the client it accompanies.

Human-aware robot navigation: A survey

Multi-model hypothesis tracking of groups of people in RGB-D data

  • Timm LinderK. Arras
  • Computer Science
    17th International Conference on Information Fusion (FUSION)
  • 2014
TLDR
This paper addresses the problem of detecting groups of people from learned social relations between individuals with the goal to reliably track group formation processes, and tracks and reason about multiple social grouping hypotheses in a recursive way.