TY - JOUR
T1 - Confidence-aware motion prediction for real-time collision avoidance1
AU - Fridovich-Keil, David
AU - Bajcsy, Andrea
AU - Fisac, Jaime F.
AU - Herbert, Sylvia L.
AU - Wang, Steven
AU - Dragan, Anca D.
AU - Tomlin, Claire J.
N1 - Funding Information:
The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This research is supported by and NSF CAREER award, the Air Force Office of Scientific Research (AFOSR), NSF’s CPS FORCES and VeHICal projects, the UC-Philippine-California Advanced Research Institute, the ONR MURI Embedded Humans and the SRC CONIX Center.
Publisher Copyright:
© The Author(s) 2019.
PY - 2020/3/1
Y1 - 2020/3/1
N2 - 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.
AB - 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.
KW - Motion planning
KW - human motion prediction
KW - robust control
KW - safety
UR - http://www.scopus.com/inward/record.url?scp=85068262870&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85068262870&partnerID=8YFLogxK
U2 - 10.1177/0278364919859436
DO - 10.1177/0278364919859436
M3 - Article
AN - SCOPUS:85068262870
SN - 0278-3649
VL - 39
SP - 250
EP - 265
JO - International Journal of Robotics Research
JF - International Journal of Robotics Research
IS - 2-3
ER -