Safe Decision-Making in Interactive Environments

Autonomous ground vehicles must safely operate in highly interactive environments with human uncertainties. Safe actions depend on context, interactions, and absolute (mathematical measures for safety) may differ from how humans perceive as safe and reliable behaviors. However, producing context-dependent and interaction-aware safe actions is non-trivial due to the following technical challenges. Challenge 1: Hardness in the identification of interaction mechanisms. When interaction mechanisms are known or can be learned, many safe learning and control techniques can be employed. However, in many interactive environments, it may be fundamentally difficult to fully identify the mechanisms of the opponent's interaction due to unobserved confounders. Challenge 2: Latent risk and latent variables. There exist latent risks (such as occlusions) and unobserved variables (e.g. awareness and intention), and safe actions depend on such factors. For example, pedestrians can decide to enter a crosswalk, but such intent may not be directly observable. Decisions that ignore such factors may experience unexpected risks. Challenge 3: Tensions between long-term safety vs. computation. Accounting for long-term outcomes in risk quantification and control is challenging due to stringent computation vs. time-horizon tradeoffs, particularly for rare events. Myopic safety can be efficiently certified, but ensuring long-term safety may require prohibitive computation. Although distribution shifts are often approached by finding actions that are robust to changes or avoid changes, much less work explores how to proactively induce desirable opponent behavior changes in interactive environments. For example, whereas humans can slowly squeeze their way through crowded environments, autonomous systems programmed to maintain worst-case distance may not find feasible solutions (e.g., freezing robot problems). Proximity can be safe or risky depending on opponents’ interaction mechanisms, but this is not captured in a simple risk measure of distance. The proposed research aims at realizing such capabilities by accounting for interaction models and anticipating unobserved unknowns in risk quantification and decision-making. Specifically, the research team proposes the following research. Thrust 1: The research team will establish an efficient risk quantification method with theoretical guarantees. The research team will leverage an integrative view of stochastic systems, MC, PDEs, and Physics-informed neural networks (PINNs) to estimate intervention risk from heterogeneous data and exploit low-dimensional structures. The research team's prior work has derived four types of long-term safe probabilities as unique solutions to deterministic linear PDEs, which characterize the relation between risk probabilities of different time horizons and initial states. PINNs with these PDE constraints have been shown to be able to infer risk probabilities beyond available data with provable generalization. Here, the research team will explore such characterization and enable long-term risk to be quantified using shorter-term interaction data. Thrust 2: The research team will develop efficient long-term safety certificates for interactive environments. While treating statistical models as mechanistic models may neglect important latent risk factors, little effort has been made to rigorously differentiate the underlying mechanistic models vs. observed statistical models in the design of safety certificates. Here, the research team will build upon their prior work on probabilistic invariance to differentiate the two models, control the risk probability using observed statistics, and handle information constraints arising from delayed and rate-limited communication.


  • English


  • Status: Active
  • Funding: $98000
  • Contract Numbers:


  • Sponsor Organizations:

    Carnegie Mellon University

    Safety21 National UTC for Promoting Safety
    Pittsburgh, PA  United States  15213

    Office of the Assistant Secretary for Research and Technology

    University Transportation Center Program
  • Managing Organizations:

    Carnegie Mellon University

    Safety21 National UTC for Promoting Safety
    Pittsburgh, PA  United States  15213
  • Project Managers:

    Stearns, Amy

  • Performing Organizations:

    Carnegie Mellon University

  • Principal Investigators:

    Nakahira, Yorie

  • Start Date: 20230701
  • Expected Completion Date: 20240630
  • Actual Completion Date: 0
  • USDOT Program: University Transportation Centers

Subject/Index Terms

Filing Info

  • Accession Number: 01900364
  • Record Type: Research project
  • Source Agency: Safety21
  • Contract Numbers: 69A3552344811
  • Files: UTC, RIP
  • Created Date: Nov 21 2023 6:30PM