Being aware of mutual influences between individuals is a major requirement a robot to efficiently operate in human populated environments. This is especially true for the navigation among humans with its mutual avoidance maneuvers. While humans easily manage this task, robotic systems are still facing problems. Most of the recent approaches concentrate on predicting the motions of humans individually and deciding afterwards. Thereby, interactivity is mostly neglected. In this work, we go one step back and focus on understanding the underlying principle of human decision making in the presence of multiple humans. Non-cooperative game theory is applied to formulate the problem of predicting the decisions of multiple humans that interact which each other during navigation. Therefore, we use the theory of Nash equilibria in static and dynamic games where different cost functions from literature rate the payoffs of the individual humans. The approach anticipates collisions and additionally reasons about several avoidance maneuvers of all humans. For the evaluation of the game theoretic approach we recorded trajectories of humans passing each other. The evaluation shows that game theory is able to reproduce the decision process of humans more accurately than a decision model that predicts humans individually.

/pdf/understanding-human-avoidance-behavior-interaction-aware-dsoyuagg8z.pdf

Understanding Human Avoidance Behavior: Interaction-Aware Decision Making Based on Game Theory

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.

/pdf/human-like-motion-planning-based-on-game-theoretic-decision-2o72zhvriz.pdf

Human-Like Motion Planning Based on Game Theoretic Decision Making

Localisation and navigation of autonomous vehicles (AVs) in static environments are now solved problems, but how to control their interactions with other road users in mixed traffic environments, especially with pedestrians, remains an open question. Recent work has begun to apply game theory to model and control AV-pedestrian interactions as they compete for space on the road whilst trying to avoid collisions. But this game theory model has been developed only in unrealistic lab environments. To improve their realism, this study empirically examines pedestrian behaviour during road crossing in the presence of approaching autonomous vehicles in more realistic virtual reality (VR) environments. The autonomous vehicles are controlled using game theory, and this study seeks to find the best parameters for these controls to produce comfortable interactions for the pedestrians. In a first experiment, participants’ trajectories reveal a more cautious crossing behaviour in VR than in previous laboratory experiments. In two further experiments, a gradient descent approach is used to investigate participants’ preference for AV driving style. The results show that the majority of participants were not expecting the AV to stop in some scenarios, and there was no change in their crossing behaviour in two environments and with different car models suggestive of car and last-mile style vehicles. These results provide some initial estimates for game theoretic parameters needed by future AVs in their pedestrian interactions and more generally show how such parameters can be inferred from virtual reality experiments.

Evaluating pedestrian interaction preferences with a game theoretic autonomous vehicle in virtual reality

We describe a formalism and algorithms for game-tree search in partially-observable Euclidean space, and implementation and tests in a scenario where a multi-agent team, called tracking agents, pursues a target agent that wants to evade the tracking agents. Our contributions include---• A formalism that combines geometric elements (agents' locations and trajectories and observable regions, and obstacles that restrict mobility and observability) with game-theoretic elements (information sets, utility functions, and strategies).• A recursive formula for information-set minimax values based on our formalism, and a implementation of the formula in a game-tree search algorithm.• A heuristic evaluation function for use at the leaf nodes of the game-tree search. It works by doing a quick lookahead search of its own, in a relaxed version of the problem.• Experimental results in 500 randomly generated trials. With the strategies generated by our heuristic, the tracking agents were more than twice as likely to know the target agent's location at the end of the game than with the strategies generated by heuristics that compute estimates of the target's possible locations.

https://www.ifaamas.org/Proceedings/aamas2010/pdf/01%20Full%20Papers/19_06_FP_0610.pdf

Strategy generation in multi-agent imperfect-information pursuit games

In this paper, we investigate the decision making of autonomous vehicles in an unsignalized intersection in presence of malicious vehicles, which are vehicles that do not respect the law by not using the proper rules of the right of way. Each vehicle computes its control input as a Nash equilibrium of a game determined by the priority order based on its own belief: each of non-malicious vehicle bases its order on the law, while a malicious one considers itself as having priority. To illustrate the effectiveness of our method, we provide numerical simulations, with different scenarios given by different cases of malicious vehicles.

Decision Making for Autonomous Vehicles at Unsignalized Intersection in Presence of Malicious Vehicles

This paper proposes a game-theory based approach in a multi-target searching using a multi-robot system in a dynamic environment. It is assumed that a rough priori probability map of the targets' distribution within the environment is given. To consider the interaction between the robots, a dynamic-programming equation is proposed to estimate the utility function for each robot. Based on this utility function, a cooperative nonzero-sum game is generated, where both pure Nash Equilibrium and mixed-strategy Equilibrium solutions are presented to achieve an optimal overall robot behaviors. A special consideration has been taken to improve the real-time performance of the game-theory based approach. Several mechanisms, such as event-driven discretization, one-step dynamic programming, and decision buffer, have been proposed to reduce the computational complexity. The main advantage of the algorithm lies in its real-time capabilities whilst being efficient and robust to dynamic environments.

https://journals.sagepub.com/doi/pdf/10.5772/6232

Yan Meng

Papers

Multi-Robot Searching using Game-Theory Based Approach