Learning from Demonstration (LfD) is a powerful method for nonroboticists
end-users to teach robots new tasks, enabling them to
customize the robot behavior. However, modern LfD techniques do
not explicitly synthesize safe robot behavior, which limits the deployability
of these approaches in the real world. To enforce safety
in LfD without relying on experts, we propose a new framework,
ShiElding with Control barrier fUnctions in inverse REinforcement
learning (SECURE), which learns a customized Control Barrier
Function (CBF) from end-users that prevents robots from taking
unsafe actions while imposing little interference with the task completion.
We evaluate SECURE in three sets of experiments. First,
we empirically validate SECURE learns a high-quality CBF from
demonstrations and outperforms conventional LfD methods on simulated
robotic and autonomous driving tasks with improvements
on safety by up to 100%. Second, we demonstrate that roboticists
can leverage SECURE to outperform conventional LfD approaches
on a real-world knife-cutting, meal-preparation task by 12.5% in
task completion while driving the number of safety violations to
zero. Finally, we demonstrate in a user study that non-roboticists
can use SECURE to efectively teach the robot safe policies that
avoid collisions with the person and prevent cofee from spilling.
more »
« less
Experimental testing of a control barrier function on an automated vehicle in live multi-lane traffic
This paper experimentally tests an implementation of a control barrier function (CBF) designed to guarantee a minimum time-gap in car following on an automated vehicle (AV) in live traffic, with a majority occurring on freeways. The CBF supervises a nominal unsafe PID controller on the AV’s velocity. The experimental testing spans two months of driving, of which 1.9 hours of data is collected in which the CBF and nominal controller are active. We find that violations of the guaranteed minimum time-gap are observed, as measured by the vehicle’s on-board radar unit. There are two distinct causes of the violations. First, in multi-lane traffic, Cut-ins from other vehicles represent external disturbances that can immediately violate the minimum guaranteed time gap provided by the CBF. When cut-ins occur, the CBF does eventually return the vehicle to a safe time gap. Second, even when cut-ins do not occur, system model inaccuracies (e.g., sensor error and delay, actuator error and delay) can lead to violations of the minimum time-gap. These violations are small relative to the violations that would have occurred using only the unsafe nominal control law.
more »
« less
- Award ID(s):
- 2135579
- NSF-PAR ID:
- 10385362
- Date Published:
- Journal Name:
- 2022 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop (DI-CPS)
- Page Range / eLocation ID:
- 31 to 35
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This paper focuses on the detection of cyber-attack on a communication channel and simultaneous radar health monitoring for a connected vehicle. A semi-autonomous adaptive cruise control (SA-ACC) vehicle is considered which has wireless communication with its immediately preceding vehicle to operate at small time-gap distances without creating string instability. However, the reliability of the wireless connectivity is critical for ensuring safe vehicle operation. The presence of two unknown inputs related to both sensor failure and cyber-attack seemingly poses a difficult estimation challenge. The dynamic system is first represented in descriptor system form. An observer with estimation error dynamics decoupled from the cyber-attack signal is developed. The performance of the observer is extensively evaluated in simulations. The estimation system is able to detect either a fault in the velocity measurement radar channel or a cyber-attack. Also, the proposed observer-based controller achieves resilient SA-ACC system under the cyber-attacks. The fundamental estimation algorithm developed herein can be extended in the future to enable cyber-attack detection in more complex connected vehicle architectures.more » « less
-
null (Ed.)With the development of the emerging Connected Vehicle (CV) technology, vehicles can wirelessly communicate with traffic infrastructure and other vehicles to exchange safety and mobility information in real time. However, the integrated communication capability inevitably increases the attack surface of vehicles, which can be exploited to cause safety hazard on the road. Thus, it is highly desirable to systematically understand design-level flaws in the current CV network stack as well as in CV applications, and the corresponding security/safety consequences so that these flaws can be proactively discovered and addressed before large-scale deployment. In this paper, we design CVAnalyzer, a system for discovering design-level flaws for availability violations of the CV network stack, as well as quantifying the corresponding security/safety consequences. To achieve this, CVAnalyzer combines the attack discovery capability of a general model checker and the quantitative threat assessment capability of a probabilistic model checker. Using CVAnalyzer, we successfully uncovered 4 new DoS (Denial-of-Service) vulnerabilities of the latest CV network protocols and 14 new DoS vulnerabilities of two CV platoon management protocols. Our quantification results show that these attacks can have as high as 99% success rates, and in the worst case can at least double the delay in packet processing, violating the latency requirement in CV communication.We implemented and validated all attacks in a real-world testbed, and also analyzed the fundamental causes to propose potential solutions. We have reported our findings in the CV network protocols to the IEEE 1609 Working Group, and the group has acknowledged the discovered vulnerabilities and plans to adopt our solutions.more » « less
-
Speed planning in a vehicle-following scenario can reduce vehicle fuel consumption even under limited traffic preview and in moderate penetration of connected autonomous vehicles (CAVs), but could also lead to colder exhaust temperature, and consequently, less efficient aftertreatment conversion. To investigate this potential trade-off, this paper presents a model predictive controller (MPC) to optimally plan in an energy-conscious way the optimal speed trajectory for a diesel car following a hypothetical lead vehicle that drives through the velocity trace of a federal test procedure. Using this energy-conscious optimal speed plan we investigate different horizons for three objective functions, including minimum acceleration, minimum fuel consumption and minimum power. Then, MPC results are compared to the trajectories obtained by dynamic programming with full knowledge of the drive cycle. As expected, longer previews lead to smoother velocity trajectories that reduce the fuel consumption by 11% when power is the objective function, if the preview is accurate. When the minimum fuel is set as the objective in the MPC, the controller coordinates to operate the engine at more efficient conditions, which increases the fuel saving to 25%. However, the extra fuel saving is shown to be achieved at the expense of high vehicle NOx emissions, since the engine operates at low speeds and high loads, where the output NOx emissions are high, when the aftertreatment catalyst is not hot enough. Finally, it is shown that the minimum power formulation leads to a better trade-off, where fuel economy can be increased without a large penalty on NOx emissions.more » « less
-
In this paper, the issue of model uncertainty in safety-critical control is addressed with a data-driven approach. For this purpose, we utilize the structure of an input-output linearization controller based on a nominal model along with a Control Barrier Function and Control Lyapunov Function based Quadratic Program (CBF-CLF-QP). Specifically, we propose a novel reinforcement learning framework which learns the model uncertainty present in the CBF and CLF constraints, as well as other control-affine dynamic constraints in the quadratic program. The trained policy is combined with the nominal model based CBF-CLF-QP, resulting in the Reinforcement Learning based CBF-CLF-QP (RL-CBF-CLF-QP), which addresses the problem of model uncertainty in the safety constraints. The performance of the proposed method is validated by testing it on an underactuated nonlinear bipedal robot walking on randomly spaced stepping stones with one step preview, obtaining stable and safe walking under model uncertainty.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/DI-CPS56137.2022.00011
