Human-inspired robot navigation in unknown dynamic environments

Pradeep, Yazhini C.; Zhu, Ming; Rosario, Manuel Del; Chen, Peter C. Y.

doi:10.1109/icma.2016.7558694

Cited by 4 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, the literature reports three main methods to evaluate the human-likeness and the social acceptance of robot navigation: (i) definition of social rules or performance parameters and, then, assessment of the adherence of the robot motion planner to these principles [54][55][56] ; (ii) comparison between simulated trajectories and observed pedestrian behavior 57 ; (iii) survey questionnaire based on a variation of the Turing test 9,58 . The main limitation of the first two methods is that they do not consider how humans perceive the robot.…”

Section: Discussionmentioning

confidence: 99%

Game theoretical trajectory planning enhances social acceptability of robots by humans

Galati

Primatesta

Grammatico

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Since humans and robots are increasingly sharing portions of their operational spaces, experimental evidence is needed to ascertain the safety and social acceptability of robots in human-populated environments. Although several studies have aimed at devising strategies for robot trajectory planning to perform safe motion in populated environments, a few efforts have measured to what extent a robot trajectory is accepted by humans. Here, we present a navigation system for autonomous robots that ensures safety and social acceptability of robotic trajectories. We overcome the typical reactive nature of state-of-the-art trajectory planners by leveraging non-cooperative game theory to design a planner that encapsulates human-like features of preservation of a personal space, recognition of groups, sequential and strategized decision making, and smooth obstacle avoidance. Social acceptability is measured through a variation of the Turing test administered in the form of a survey questionnaire to a pool of 691 participants. Comparison terms for our tests are a state-of-the-art navigation algorithm (Enhanced Vector Field Histogram, VFH) and purely human trajectories. While all participants easily recognized the non-human nature of VFH-generated trajectories, the distinction between game-theoretical trajectories and human ones were hardly revealed. Our results mark a strong milestone toward the full integration of robots in social environments.

show abstract

Section: Discussionmentioning

confidence: 99%

Game theoretical trajectory planning enhances social acceptability of robots by humans

Galati

Primatesta

Grammatico

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Additionally, they counted the number of collisions. Similar measures were used by Pradeep et al [65]. In simulations, they evaluated the number of collisions, path irregularity, and the average 'safety threat' (a value dependent on the relative position of the nearest object).…”

Section: Related Workmentioning

confidence: 99%

Human-Like Motion Planning Based on Game Theoretic Decision Making

Turnwald

Wollherr

2018

Int J of Soc Robotics

View full text Add to dashboard Cite

Robot motion planners are increasingly being equipped with an intriguing property: human likeness. This property can enhance human-robot interactions and is essential for a convincing computer animation of humans. This paper presents a (multi-agent) motion planner for dynamic environments that generates human-like motion. The presented motion planner stands out against other motion planners by explicitly modeling human-like decision making and taking interdependencies between individuals into account, which is achieved by applying game theory. Non-cooperative games and the concept of a Nash equilibrium are used to formulate the decision process that describes human motion behavior while walking in a populated environment. We evaluate whether our approach generates human-like motions through two experiments: a video study showing simulated, moving pedestrians, wherein the participants are passive observers, and a collision avoidance study, wherein the participants interact within virtual reality with an agent that is controlled by different motion planners. The experiments are designed as variations of the Turing test, which determines whether participants can differentiate between human motions and artificially generated motions. The results of both studies coincide and show that the participants could not distinguish between human motion behavior and our artificial behavior based on game theory. In contrast, the participants could distinguish human motions from motions based on established planners, such as the reciprocal velocity obstacles or social forces.

show abstract