Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction

Nishimura, Haruki; Ivanovic, Boris; Gaidon, Adrien; Pavone, Marco; Schwager, Mac

doi:10.1109/iros45743.2020.9341469

Cited by 31 publications

(24 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The common approach to interactive trajectory planning is for a robot to make predictions of the future trajectories of other agents and plan reactively [7,8,9,10,11]. Planning reactively will make the agents decoupled and simplify the control problem.…”

Section: A Interactive Trajectory Planningmentioning

confidence: 99%

Potential iLQR: A Potential-Minimizing Controller for Planning Multi-Agent Interactive Trajectories

Kavuncu¹,

Ayberk²,

Mehr³

2021

Robotics: Science and Systems XVII

View full text Add to dashboard Cite

Many robotic applications involve interactions between multiple agents where an agent's decisions affect the behavior of other agents. Such behaviors can be captured by the equilibria of differential games which provide an expressive framework for modeling the agents' mutual influence. However, finding the equilibria of differential games is in general challenging as it involves solving a set of coupled optimal control problems. In this work, we propose to leverage the special structure of multi-agent interactions to generate interactive trajectories by simply solving a single optimal control problem, namely, the optimal control problem associated with minimizing the potential function of the differential game. Our key insight is that for a certain class of multi-agent interactions, the underlying differential game is indeed a potential differential game for which equilibria can be found by solving a single optimal control problem. We introduce such an optimal control problem and build on single-agent trajectory optimization methods to develop a computationally tractable and scalable algorithm for planning multi-agent interactive trajectories. We will demonstrate the performance of our algorithm in simulation and show that our algorithm outperforms the state-of-the-art game solvers. To further show the real-time capabilities of our algorithm, we will demonstrate the application of our proposed algorithm in a set of experiments involving interactive trajectories for two quadcopters.

show abstract

Section: A Interactive Trajectory Planningmentioning

confidence: 99%

Potential iLQR: A Potential-Minimizing Controller for Planning Multi-Agent Interactive Trajectories

Kavuncu¹,

Ayberk²,

Mehr³

2021

Robotics: Science and Systems XVII

View full text Add to dashboard Cite

show abstract

“…While existing metrics are useful for evaluating the performance of trajectory forecasting methods in isolation, there are important considerations that arise during real-world deployment. Some examples include handling perception uncertainty in prediction [22,23,24] and integrating prediction and planning [3,25,26,27,28]). Most importantly, in this work we focus on the fact that prediction errors are asymmetric in the real world, i.e., predictions with the same metric accuracy may lead to vastly different outcomes, an example of which is illustrated in Figure 1 (b) and (c).…”

Section: Related Workmentioning

confidence: 99%

Rethinking Trajectory Forecasting Evaluation

Ivanovic,

Pavone

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Forecasting the behavior of other agents is an integral part of the modern robotic autonomy stack, especially in safety-critical scenarios with humanrobot interaction, such as autonomous driving. In turn, there has been a significant amount of interest and research in trajectory forecasting, resulting in a wide variety of approaches. Common to all works, however, is the use of the same few accuracy-based evaluation metrics, e.g., displacement error and log-likelihood. While these metrics are informative, they are task-agnostic and predictions that are evaluated as equal can lead to vastly different outcomes, e.g., in downstream planning and decision making. In this work, we take a step back and critically evaluate current trajectory forecasting metrics, proposing task-aware metrics as a better measure of performance in systems where prediction is being deployed. We additionally present one example of such a metric, incorporating planningawareness within existing trajectory forecasting metrics.

show abstract

“…While existing metrics are useful for evaluating the performance of trajectory forecasting methods in isolation, there are important considerations that arise during real-world deployment. Some examples include handling perception uncertainty in prediction [24], [25], [26] and integrating prediction and planning [3], [27], [28], [29], [30]. Most importantly, in this work we focus on the fact that prediction errors are asymmetric in the real world, i.e., predictions with the same metric accuracy may lead to vastly different outcomes, an example of which is illustrated in Fig.…”

Section: Related Workmentioning

confidence: 99%

Injecting Planning-Awareness into Prediction and Detection Evaluation

Ivanovic¹,

Pavone²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Detecting other agents and forecasting their behavior is an integral part of the modern robotic autonomy stack, especially in safety-critical scenarios entailing human-robot interaction such as autonomous driving. Due to the importance of these components, there has been a significant amount of interest and research in perception and trajectory forecasting, resulting in a wide variety of approaches. Common to most works, however, is the use of the same few accuracy-based evaluation metrics, e.g., intersection-over-union, displacement error, log-likelihood, etc. While these metrics are informative, they are task-agnostic and outputs that are evaluated as equal can lead to vastly different outcomes in downstream planning and decision making. In this work, we take a step back and critically assess current evaluation metrics, proposing task-aware metrics as a better measure of performance in systems where they are deployed. Experiments on an illustrative simulation as well as real-world autonomous driving data validate that our proposed task-aware metrics are able to account for outcome asymmetry and provide a better estimate of a model's closedloop performance.

show abstract

Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction

Cited by 31 publications

References 39 publications

Potential iLQR: A Potential-Minimizing Controller for Planning Multi-Agent Interactive Trajectories

Potential iLQR: A Potential-Minimizing Controller for Planning Multi-Agent Interactive Trajectories

Rethinking Trajectory Forecasting Evaluation

Injecting Planning-Awareness into Prediction and Detection Evaluation

Contact Info

Product

Resources

About