Confidence-aware motion prediction for real-time collision avoidance¹

Abstract

One of the most difficult challenges in robot motion planning is to account for the behavior of other moving agents, such as humans. Commonly, practitioners employ predictive models to reason about where other agents are going to move. Though there has been much recent work in building predictive models, no model is ever perfect: an agent can always move unexpectedly, in a way that is not predicted or not assigned sufficient probability. In such cases, the robot may plan trajectories that appear safe but, in fact, lead to collision. Rather than trust a model’s predictions blindly, we propose that the robot should use the model’s current predictive accuracy to inform the degree of confidence in its future predictions. This model confidence inference allows us to generate probabilistic motion predictions that exploit modeled structure when the structure successfully explains human motion, and degrade gracefully whenever the human moves unexpectedly. We accomplish this by maintaining a Bayesian belief over a single parameter that governs the variance of our human motion model. We couple this prediction algorithm with a recently proposed robust motion planner and controller to guide the construction of robot trajectories that are, to a good approximation, collision-free with a high, user-specified probability. We provide extensive analysis of the combined approach and its overall safety properties by establishing a connection to reachability analysis, and conclude with a hardware demonstration in which a small quadcopter operates safely in the same space as a human pedestrian.

Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning in Dynamic Environments

“…Our proposed approach decouples motion prediction and trajectory planning to achieve decentralized and communication-free collision avoidance. Such a decoupling is also seen in [19], [20], where the motion prediction of humans are used to plan a safe trajectory for the ego robot. Motion prediction for decision-making agents has drawn significant research efforts over the past years, with most works focusing on human trajectory prediction [21].…”

FaSTrack:A Modular Framework for Real-Time Motion Planning and Guaranteed Safe Tracking

“…If the planning model is not allowed to stop instantaneously, recursive safety can be ensured by methods such as [48], [49]. FaSTrack applied to dynamic environments with humans is explored in [50], [51], and is paired with work on sequential trajectory tracking [52] to handle multi-human, multi-robot environments [53].…”

Provably Safe and Efficient Motion Planning with Uncertain Human Dynamics

“…Our method focuses on both estimating the uncertainty in human models and conservatively propagating it forward in time for safe planning. Fisac et al [10], Fridovich-Keil et al [12] developed a confidence-aware safe HAMP algorithm. There are a couple of differences between their work and ours.…”