AI Safety Research

Stefano Ermon

Assistant Professor of Computer Science

Fellow of the Woods Institute for the Environment

Stanford University

Project: Robust probabilistic inference engines for autonomous agents

Amount Recommended:    $250,000

Project Summary:

As we close the loop between sensing-reasoning-acting, autonomous agents such as self-driving cars are required to act intelligently and adaptively in increasingly complex and uncertain real-world environments. To make sensible decisions under uncertainty, agents need to reason probabilistically about their environments, e.g., estimate the probability that a pedestrian will cross or that a car will change lane. Over the past decades, AI research has made tremendous progress in automated reasoning. Existing technology achieves super-human performance in numerous domains, including chess-playing and crossword-solving. Unfortunately, current approaches do not provide worst-case guarantees on the quality of the results obtained. For example, it is not possible to rule out completely unexpected behaviors or catastrophic failures. Therefore, we propose to develop novel reasoning technology focusing on soundness and robustness. This research will greatly improve the reliability and safety of next-generation autonomous agents.

Technical Abstract: 

To cope with the uncertainty and ambiguity of real world domains, modern AI systems rely heavily on statistical approaches and probabilistic modeling. Intelligent autonomous agents need to solve numerous probabilistic reasoning tasks, ranging from probabilistic inference to stochastic planning problems. Safety and reliability depend crucially on having both accurate models and sound reasoning techniques. To date, there are two main paradigms for probabilistic reasoning: exact decomposition-based techniques and approximate methods such as variational and MCMC sampling. Neither of them is suitable for supporting autonomous agents interacting with complex environments safely and reliably. Decomposition-based techniques are accurate but are not scalable. Approximate techniques are more scalable, but in most cases do not provide formal guarantees on the accuracy. We therefore proposes to develop probabilistic reasoning technology which is both scalable and provides formal guarantees, i.e., “certificates” of accuracy, as in formal verification. This research will bridge probabilistic and deterministic reasoning, drawing from their respective strengths, and has the potential to greatly improve the reliability and safety of AI and cyber-physical systems.

How Self-Driving Cars Use Probability

Even though human drivers don’t consciously think in terms of probabilities, we observe our environment and make decisions based on the likelihood of certain things happening. A driver doesn’t calculate the probability that the sports car behind her will pass her, but through observing the car’s behavior and considering similar situations in the past, she makes her best guess.

We trust probabilities because it is the only way to take action in the midst of uncertainty.

Autonomous systems such as self-driving cars will make similar decisions based on probabilities, but through a different process. Unlike a human who trusts intuition and experience, these autonomous cars calculate the probability of certain scenarios using data collectors and reasoning algorithms.

How to Determine Probability

Stefano Ermon, a computer scientist at Stanford University, wants to make self-driving cars and autonomous systems safer and more reliable by improving the way they reason probabilistically about their environment. He explains, “The challenge is that you have to take actions and you don’t know what will happen next. Probabilistic reasoning is just the idea of thinking about the world in terms of probabilities, assuming that there is uncertainty.”

There are two main components to achieve safety. First, the computer model must collect accurate data, and second, the reasoning system must be able to draw the right conclusions from the model’s data.

Ermon explains, “You need both: to build a reliable model you need a lot of data, and then you need to be able to draw the right conclusions based on the model, and that requires the artificial intelligence to think about these models accurately. Even if the model is right, but you don’t have a good way to reason about it, you can do catastrophic things.”

For example, in the context of autonomous vehicles, models use various sensors to observe the environment and collect data about countless variables, such as the behavior of the drivers around you, potholes and other obstacles in front of you, weather conditions—every possible data point.

A reasoning system then interprets this data. It uses the model’s information to decide whether the driver behind you is dangerously aggressive, if the pothole ahead will puncture your tire, if the rain is obstructing visibility, and the system continuously changes the car’s behavior to respond to these variables.

Consider the aggressive driver behind you. As Ermon explains, “Somehow you need to be able to reason about these models. You need to come up with a probability. You don’t know what the car’s going to do but you can estimate, and based on previous behavior you can say this car is likely to cut the line because it has been driving aggressively.”

Improving Probabilistic Reasoning

Ermon is creating strong algorithms that can synthesize all of the data that a model produces and make reliable decisions.

As models improve, they collect more information and capture more variables relevant to making these decisions. But as Ermon notes, “the more complicated the model is, the more variables you have, the more complicated it becomes to make the optimal decisions based on the model.”

Thus as the data collection expands, the analysis must also improve. The artificial intelligence in these cars must be able to reason with this increasingly complex data.

And this reasoning can easily go wrong. “You need to be very precise when computing these probabilities,” Ermon explains. “If the probability that a car cuts into your lane is 0.1, but you completely underestimate it and say it’s 0.01, you might end up making a fatal decision.”

To avoid fatal decisions, the artificial intelligence must be robust, but the data must also be complete. If the model collects incomplete data, “you have no guarantee that the number that you get when you run this algorithm has anything to do with the actual probability of that event,” Ermon explains.

The model and the algorithm entirely depend on each other to produce the optimal decision. If the model is incomplete and fails to capture the black ice in front of you, no reasoning system will be able to make a safe decision. And even if the model captures the black ice and every other possible variable, if the reasoning system cannot handle the complexity of this data, again the car will fail.

How Safe Will Autonomous Systems Be?

The technology in self-driving cars has made huge leaps lately, and Ermon is hopeful. “Eventually, as computers get better and algorithms get better and the models get better, hopefully we’ll be able to prevent all accidents,” he suggests.

However, there are still fundamental limitations on probabilistic reasoning. “Most computer scientists believe that it is impossible to come up with the silver bullet for this problem, an optimal algorithm that is so powerful that it can reason about all sorts of models that you can think about,” Ermon explains. “That’s the key barrier.”

But despite this barrier, self-driving cars will soon be available for consumers. Ford, for one, has promised to put its self-driving cars on the road by 2021. And while most computer scientists expect these cars to be far safer than human drivers, their success depends on their ability to reason probabilistically about their environment.

As Ermon explains, “You need to be able to estimate these kinds of probabilities because they are the building blocks that you need to make decisions.”

This article is part of a Future of Life series on the AI safety research grants, which were funded by generous donations from Elon Musk and the Open Philanthropy Project.


  1. Achim, T, et al. Beyond parity constraints: Fourier analysis of hash functions for inference. Proceedings of The 33rd International Conference on Machine Learning, pages 2254–2262, 2016.
    • New analysis of hash functions families for inference in terms of Fourier analysis.
  2. Hsu, L.K., et al. Tight variational bounds via random projections and i-projections. Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, pages 1087–1095, 2016.
    • This paper discusses new techniques to obtain provable guarantees from traditional variational inference algorithms, using random projections and hash functions.
  3. Kim, C., et al. Exact sampling with integer linear programs and random perturbations. Proc. 30th AAAI Conference on Artificial Intelligence, 2016.
    • This paper discusses development of a new exact inference algorithm for discrete probabilistic models that can leverage the reasoning power (and proof certificates) of integer linear programming solvers.
  4. S. Zhao, et al. Closing the gap between short and long xors for model counting. Thirtieth AAAI Conference on Artificial Intelligence, 2016.
    • New analysis of error correcting codes for inference, showing that low-density parity check codes can be used and provide the same accuracy guarantees as traditional (dense) ones, but are much more efficient in practice.

Ongoing Projects/Recent Progress

This team will proceed as planned for year 2, expanding the scope of probabilistic inference algorithms with provable guarantees on the accuracy. In particular, they plan to explore how to apply these new ideas to obtain provable worst-case guarantees in decision-making under uncertainty frameworks.

Click here to add your own text