Interests

Up-to-date projects can by found on my group’s website:
Human-Centered Autonomy Lab.
Somewhat out of Date Research

My research focuses on exploring and uncovering structure in complex human-robot systems to create more intelligent, interactive autonomy. I develop rigorous human models and control frameworks that mimic the positive properties of human agents, while compensating for their shortcomings with safety guarantees. Most of my work centers around autonomous vehicles, considering how they may best integrate and operate in mixed environment, with both humans and autonomous vehicles on the road.

My research agenda aims to address these points by combining ideas from robotics, artificial intelligence, and control applied to human-robot systems and the transportation domain. The current major focuses are:

  • Validating the autonomous systems using novel tools to find likely failures as well as rigorous experiments in high-fidelity simulation, immersive testbeds, and fully outfitted autonomous test vehicles;
  • Developing robust models of human-robot systems that capture the highly stochastic behaviors of humans for use in semi- and fully autonomous control;
  • Designing interactive control policies for intelligent systems in multi-agent settings, which can be applied to shared control schemes or fully autonomous systems that interact and collaborate with humans; and
  • Learning from human behaviors for improved intelligent systems by formalizing methods to integrate people as sensors in perception modules and learning control policies based on expert human actions.

For up to date research, check out my publication list!

Human Centered PerceptionLearning for Autonomous SystemsRigorous ValidationEmpirical Reachable SetsBehavior Modeling
Much like humans in the real world, who observe other drivers and make inferences, we have designed a framework that treats human drivers as sensors to provide environment information to our intelligent system. We used probabilistic learning methods to estimate a sensor model that captures how people dynamically respond to pedestrians (i.e., learning the relationship between environment state and action), so that driver’s actions can then serve as a proxy for detection. This framework has shown significantly improvement in overall environment awareness.
Selected Papers
  • Afolabi, Oladapo, Katherine Driggs-Campbell, Roy Dong, Mykel J Kochenderfer, and S Shankar Sastry. “People as Sensors: Imputing Maps from Human Actions.” In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018.
Despite recent advances in learning and artificial intelligence, there remain many concerns in learning approaches to decision making and control that make them unreliable for safety critical systems. To address this, we have worked to improve learning algorithms to improve the safety and robustness of the resulting decision making and control policies.

Specifically, we have recently been considering sampling and training paradigms that will improve deep reinforcement and imitation learning policies. Through this work, we have made the following contributions: (1) we have considered a robust control take on deep RL, using adversarial reinforcement learning to improve model mismatch and safe transfer; and (2) we have improve interactive imitation learning by using a Bayesian approach that accounts for model uncertainty in the learning process and improves the quality of collected demonstrations obtained from human experts.

Selected Papers
  • Kelly, Michael, Chelsea Sidrane, Katherine Driggs-Campbell, and Mykel J Kochenderfer. “HG-DAgger: Interactive Imitation Learning with Human Experts.” NeurIPS Workshop on Imitation Learning and Its Challenges in Robotics: arXiv:1810.02890, 2018.
  • Ma, Xiaobai, Katherine Driggs-Campbell, and Mykel J Kochenderfer. “Improved Robustness and Safety for Autonomous Vehicle Control with Adversarial Reinforcement Learning.” In IEEE Intelligent Vehicles Symposium (IV), 2018.
  • Menda, Kunal, Katherine Driggs-Campbell, and Mykel J Kochenderfer. “EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning.” Technical Report, arXiv:1807.08364, 2018.
Before autonomous systems are unleashed into public domain, we must have a good understanding of where their vulnerabilities are and how likely they are to fail. However, many safety critical systems (like autonomous vehicles) suffer from very rare but high risk failures, meaning that it is very difficult to validate these systems by traditional means. To overcome this, we have been investigating an approach called adaptive stress testing to actively search for failure modes in simulation. This method uses reinforcement learning to control disturbances in your simulation to find the most likely failure. This has been applied to aircraft collision avoidance systems and to autonomous vehicles.

Selected Papers
  • Xiaobai Ma, Mark Koren, Ritchie Lee, Katherine Driggs-Campbell, and Mykel J. Kochenderfer. “Adaptive Stress Testing Toolbox.” To be released in early 2019!
Behavior prediction remains one of the open problems for autonomous vehicles. Human driven vehicles (or generally the human-in-the-loop system) must be modeled in an accurate and precise manner that is easily integrated into control frameworks. Our developed driver modeling framework estimates the empirical reachable set, which is an alternative look at a classic control theoretic safety metric. This allows us to: (1) predict driving behavior over long time horizons with very high accuracy; (2) apply intervention schemes for semi-autonomous vehicles; and (3) mimic nuanced interactions between humans and autonomy in cooperative maneuvers.
Selected Papers
  • Katherine Driggs-Campbell, R. Dong, and R. Bajcsy. “Robust, Informative Human-in-the-Loop Predictions via Empirical Reachable Sets,” in IEEE Transactions on Intelligent Vehicles, 2018.
  • Driggs-Campbell, Katherine, Vijay Govindarajan, and Ruzena Bajcsy. “Integrating Intuitive Driver Models in Autonomous Planning for Interactive Maneuvers.” IEEE Transactions on Intelligent Transportation Systems 18, no. 12 (2017): 3461–3472.
  • Govindarajan, Vijay, Katherine Driggs-Campbell, and Ruzena Bajcsy. “Data-Driven Reachability Analysis for Human-in-the-Loop Systems.” In IEEE Conference on Decision and Control (CDC), 2017.
  • Driggs-Campbell, Katherine, Victor Shia, and Ruzena Bajcsy. “Improved Driver Modeling for Human-in-the-Loop Vehicular Control.” In IEEE International Conference on Robotics and Automation (ICRA), 2015.
To create autonomous systems that smoothly interact with human agents, the humans themselves must be carefully modeled. We have investigated a number of engineering approaches to design models and interactive systems, but also consider human factors, to ensure the systems reliably work in practice. The focuses of this work have considered: (1) human-in-the-loop test beds for data collection and empirical validation; (2) estimating and predicting discrete modes of behavior in vehicles; and (3) predicting human driver responses to conveyed intent.

By effectively designing autonomous systems that keep the user in mind, we can: improve driving performance while handing off control between the automation and the human driver; increase overall trust in the automation; and improve the predictability of the autonomous actions and overall situational awareness.

Selected Papers
  • Govindarajan, Vijay, Katherine Driggs-Campbell, and Ruzena Bajcsy. “Affective Driver State Monitoring for Personalized, Adaptive ADAS.” In IEEE International Conference on Intelligent Transportation Systems (ITSC), 2018.
  • Rezvani, Tara, Katherine Driggs-Campbell, and Ruzena Bajcsy. “Optimizing Interaction between Humans and Autonomy via Information Constraints on Interface Design.” In IEEE International Conference on Intelligent Transportation Systems (ITSC), 2017.
  • Driggs-Campbell, Katherine, and Ruzena Bajcsy. “Identifying Modes of Intent from Driver Behaviors in Dynamic Environments.” In IEEE International Conference on Intelligent Transportation Systems (ITSC), 2015.
  • Sadigh, Dorsa, Katherine Driggs-Campbell, Alberto Puggelli, Wenchao Li, Victor Shia, Ruzena Bajcsy, Alberto L Sangiovanni-Vincentelli, S Shankar Sastry, and Sanjit A Seshia. “Data-Driven Probabilistic Modeling and Verification of Human Driver Behavior,” 2014.