Social-aware robot navigation in urban environments

Ferrer, Gonzalo; Garrell, Anaís; Sanfeliu, Alberto

doi:10.1109/ecmr.2013.6698863

Cited by 80 publications

(48 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6 is depicted a function of the social-force module |f int obs | for each set of parameters with respect to distance to target. Additionally, we can observe the obtained social-force parameters for each θ k that resulted in the minimization of (11). We can appreciate that the separation of the clusters is not so significant, despite the noisy conditions and the variability of humans.…”

Section: Methodsmentioning

confidence: 92%

“…During experimentation in real scenarios [11], [12] we observed a high variability in human motion and it served as the motivation to develop the present work. Given the high variability of human behavior, it is difficult to accurately predict human motion using the same set of parameters θ, since there appear a clear difference between predictions and observations.…”

Section: Behavior Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Behavior estimation for a complete framework for human motion prediction in crowded environments

Ferrer

Sanfeliu

2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Abstract-In the present work, we propose and validate a complete probabilistic framework for human motion prediction in urban or social environments. Additionally, we formulate a powerful and useful tool: the human motion behavior estimator. Three different basic behaviors have been detected: Aware, Balanced and Unaware. Our approach is based on the Social Force Model (SFM) and the intentionality prediction BHMIP. The main contribution of the present work is to make use of the behavior estimator for formulating a reliable prediction framework of human trajectories under the influence of dynamic crowds, robots, and in general any moving obstacle. Accordingly, we have demonstrated the great performance of our long-term prediction algorithm, in real scenarios, comparing to other prediction methods.

show abstract

Section: Methodsmentioning

confidence: 92%

Section: Behavior Estimationmentioning

confidence: 99%

Behavior estimation for a complete framework for human motion prediction in crowded environments

Ferrer

Sanfeliu

2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…We propose a metric that measures social disturbances while navigating: the social work [18]. The amount of social work carried out by the robot from t ini to t horizon :…”

Section: F Cost Function and Path Selectionmentioning

confidence: 99%

“…We have compared our approach with a reactive planner proposed in [18], which takes into account people on the scene. We have compared three different values as can be seen in Fig.…”

Section: B Simulations Testingmentioning

confidence: 99%

Proactive kinodynamic planning using the Extended Social Force Model and human motion prediction in urban environments

Ferrer

Sanfeliu

2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

Self Cite

View full text Add to dashboard Cite

Abstract-This paper presents a novel approach for robot navigation in crowded urban environments where people and objects are moving simultaneously while a robot is navigating. Avoiding moving obstacles at their corresponding precise moment motivates the use of a robotic planner satisfying both dynamic and nonholonomic constraints, also referred as kynodynamic constraints. We present a proactive navigation approach with respect its environment, in the sense that the robot calculates the reaction produced by its actions and provides the minimum impact on nearby pedestrians. As a consequence, the proposed planner integrates seamlessly planning and prediction and calculates a complete motion prediction of the scene for each robot propagation. Making use of the Extended Social Force Model (ESFM) allows an enormous simplification for both the prediction model and the planning system under differential constraints. Simulations and real experiments have been carried out to demonstrate the success of the proactive kinodynamic planner.

show abstract

“…For example, reciprocal velocity obstacle (RVO) [12] is a reactionbased method that adjusts each agent's velocity vector to ensure collision-free navigation. However, since reactionbased methods do not consider evolution of the neighboring agents' future states, they are short-sighted in time and have been found to create oscillatory and unnatural behaviors in certain situations [10], [13].…”

Section: Introductionmentioning

confidence: 99%

Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning

Chen

Miao

Everett

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

492

364

View full text Add to dashboard Cite

Abstract-Finding feasible, collision-free paths for multiagent systems can be challenging, particularly in noncommunicating scenarios where each agent's intent (e.g. goal) is unobservable to the others. In particular, finding time efficient paths often requires anticipating interaction with neighboring agents, the process of which can be computationally prohibitive. This work presents a decentralized multiagent collision avoidance algorithm based on a novel application of deep reinforcement learning, which effectively offloads the online computation (for predicting interaction patterns) to an offline learning procedure. Specifically, the proposed approach develops a value network that encodes the estimated time to the goal given an agent's joint configuration (positions and velocities) with its neighbors. Use of the value network not only admits efficient (i.e., real-time implementable) queries for finding a collisionfree velocity vector, but also considers the uncertainty in the other agents' motion. Simulation results show more than 26% improvement in paths quality (i.e., time to reach the goal) when compared with optimal reciprocal collision avoidance (ORCA), a state-of-the-art collision avoidance strategy.

show abstract

Social-aware robot navigation in urban environments

Cited by 80 publications

References 25 publications

Behavior estimation for a complete framework for human motion prediction in crowded environments

Behavior estimation for a complete framework for human motion prediction in crowded environments

Proactive kinodynamic planning using the Extended Social Force Model and human motion prediction in urban environments

Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning

Contact Info

Product

Resources

About