Search for: All records

When interacting with other non-competitive decision-making agents, it is critical for an autonomous agent to have inferable behavior: Their actions must convey their intention and strategy. For example, an autonomous car's strategy must be inferable by the pedestrians interacting with the car. We model the inferability problem using a repeated bimatrix Stackelberg game with observations where a leader and a follower repeatedly interact. During the interactions, the leader uses a fixed, potentially mixed strategy. The follower, on the other hand, does not know the leader's strategy and dynamically reacts based on observations that are the leader's previous actions. In the setting with observations, the leader may suffer from an inferability loss, i.e., the performance compared to the setting where the follower has perfect information of the leader's strategy. We show that the inferability loss is upper-bounded by a function of the number of interactions and the stochasticity level of the leader's strategy, encouraging the use of inferable strategies with lower stochasticity levels. As a converse result, we also provide a game where the required number of interactions is lower bounded by a function of the desired inferability loss. 

Effectively predicting intent and behavior requires inferring leadership in multi-agent interactions. Dynamic games provide an expressive theoretical framework for modeling these interactions. Employing this framework, we propose a novel method to infer the leader in a two-agent game by observing the agents’ behavior in complex, long-horizon interactions. We make two con- tributions. First, we introduce an iterative algorithm that solves dynamic two-agent Stackelberg games with nonlinear dynamics and nonquadratic costs, and demonstrate that it consistently converges in repeated trials. Second, we propose the Stackelberg Leadership Filter (SLF), an online method for identifying the leading agent in interactive scenarios based on observations of the game interactions. We validate the leadership filter’s efficacy on simulated driving scenarios to demonstrate that the SLF can draw conclusions about leadership that match right-of-way expectations. 

Contingency planning, wherein an agent generates a set of possible plans conditioned on the outcome of an uncertain event, is an increasingly popular way for robots to act under uncertainty. In this work we take a game-theoretic perspective on contingency planning, tailored to multi-agent scenarios in which a robot’s actions impact the decisions of other agents and vice versa. The resulting contingency game allows the robot to efficiently interact with other agents by generating strategic motion plans conditioned on multiple possible intents for other actors in the scene. Contingency games are parameterized via a scalar variable which represents a future time when intent uncertainty will be resolved. By estimating this parameter online, we construct a game-theoretic motion planner that adapts to changing beliefs while anticipating future certainty. We show that existing variants of game-theoretic planning under uncertainty are readily obtained as special cases of contingency games. Through a series of simulated autonomous driving scenarios, we demonstrate that contingency games close the gap between certainty-equivalent games that commit to a single hypothesis and non-contingent multi-hypothesis games that do not account for future uncertainty reduction. 

We consider the problem of trajectory planning for optimal relative orbit determination in the cislunar environment. The recent interest in cislunar space has created a need to develop autonomous tracking technologies that can maintain situational awareness of this dynamically complex regime. Optical sensors provide an ideal observation platform because of their low cost and versatility in tracking both cooperative and non-cooperative space objects. The estimation performance of an optical observer can be significantly enhanced through manuevering. This work develops a trajectory planning tool, compatible with low-thrust propulsion, for tracking one or multiple targets operating in proximity to the observer. We formulate an objective function that is a convex combination of the mutual information between target states and measurements, and the low-thrust control effort. The subsequent optimal control problem is solved via direct collocation using the successive convexification algorithm, which, we argue, is well suited for a potential onboard trajectory planning application. We demonstrate the tool for several relevant scenarios with one and multiple targets operating around periodic orbits in the circular restricted three-body problem. A sequential estimator's performance is evaluated using the Cramer-Rao lower bound and, compared to a purely passive observer, we show that optimizing the observer's trajectory can decrease this bound by up to several orders of magnitude within a planning window. This investigation provides an initial proof-of-concept to future onboard planning technologies for relative tracking in the cislunar domain.