New Math Method Helps Robots and Self-Driving Cars Predict Better
This could make self-driving cars safer and delivery robots smarter.
Moving horizon estimation (MHE) is an estimation technique that formulates an optimization problem over a past horizon to find the states that require the minimum disturbances and noise to be feasible with the dynamics and measurements. For hybrid systems with both continuous and discrete states, this yields a mixed-integer program for the MHE, which can be difficult both to formulate and solve online under computational limitations.
This paper shows how the hybrid zonotope representation for mixed-integer sets can be used to efficiently construct the feasible space for the program using reachability-based calculations for piecewise affine systems, without requiring conversion to a mixed logical dynamical system. A method for lifting the state space to explicitly estimate the dynamic mode is also presented.
The proposed approach is evaluated in two numerical examples. Comparison against a standard mixed logical dynamical systems approach shows the proposed method can be solved orders of magnitude faster for one of the example problems.
- New math method improves how robots and self-driving cars predict their surroundings.
- It handles both smooth and sudden changes, which is hard for current systems.
- Still experimental, so not in products yet, but could lead to safer autonomous tech.
Why It Matters
Better prediction means safer self-driving cars and more efficient robots, potentially saving lives and money.