LACART: Lookahead-Augmented Collision Avoidance and Reference Tracking Strategies for Safety-Critical Robots
LACART: Lookahead-Augmented Collision Avoidance and Reference Tracking Strategies for Safety-Critical Robots
This research introduces LACART, a method integrating lookahead-based control barrier functions, relaxed control Lyapunov functions, and quadratic programming to enhance collision avoidance and reference tracking for autonomous racing. The approach handles circular obstacles and track boundaries within a unified optimization framework. Comparative simulations indicate similar full-track paths with reduced median computation times (0.31 ms per step vs. 0.33 ms) compared to Huang et al., and a 1:43-scale vehicle demonstration achieved a 25 Hz control rate using camera-based estimation and wireless actuation.
The paper presents a control strategy combining lookahead-based control barrier functions and quadratic programming for autonomous racing, with simulation results showing lower median computation times than a prior method.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S3
- Control
- Reported autonomousOpen source S2
Reported numbers
computation time per step
0.31
View original evidence
for obstacle avoidance and reference tracking. The method handles circular obstacles and track boundaries in a common optimisation layer. Comparative simulation results against Huang \emph{et al.} \cite{r9} show similar full-track paths and lower median computation times: 0.31 versus 0.33 ms per step and 0.023 versus 0.025 ms per QP solve. The dissertation further demonstrates a 1:43-scale vehicle with camera-based
Open source S3computation time per QP solve
0.023
View original evidence
for obstacle avoidance and reference tracking. The method handles circular obstacles and track boundaries in a common optimisation layer. Comparative simulation results against Huang \emph{et al.} \cite{r9} show similar full-track paths and lower median computation times: 0.31 versus 0.33 ms per step and 0.023 versus 0.025 ms per QP solve. The dissertation further demonstrates a 1:43-scale vehicle with camera-based
Open source S3control rate
25
View original evidence
estimation and wireless actuation at a reported 25 Hz control rate. We identify the conditions linking lookahead-point clearance to body clearance, illustrate hardware limitations, and propose a recorded demonstration of safety intervention and recovery. The contribution targets ground-robot collision avoidance and real-time safety monitoring.
Open source S4
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
for obstacle avoidance and reference tracking. The method handles circular obstacles and track boundaries in a common optimisation layer. Comparative simulation results against Huang \emph{et al.} \cite{r9} show similar full-track paths and lower median computation times: 0.31 versus 0.33 ms per step and 0.023 versus 0.025 ms per QP solve. The dissertation further demonstrates a 1:43-scale vehicle with camera-based
Open source S3
arXiv:2611.09640v1 Announce Type: new Abstract: Autonomous racing provides a demanding testbed for collision avoidance under tight geometric and computational constraints. Building on a recent conference contribution and a master's dissertation, LACART combines lookahead-based control barrier functions (CBFs), a relaxed control Lyapunov function (CLF), and quadratic programming (QP) to modify nominal vehicle commands
Open source S2
estimation and wireless actuation at a reported 25 Hz control rate. We identify the conditions linking lookahead-point clearance to body clearance, illustrate hardware limitations, and propose a recorded demonstration of safety intervention and recovery. The contribution targets ground-robot collision avoidance and real-time safety monitoring.
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org