3 papers
cs.RO2025
Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Tracking
Pratik Kunapuli, Jake Welde, Dinesh Jayaraman +1
Learning-based control approaches like reinforcement learning (RL) have recently produced a slew of impressive results for tasks like quadrotor trajectory tracking and drone racing…
cs.RO2025
Leveraging Symmetry to Accelerate Learning of Trajectory Tracking Controllers for Free-Flying Robotic Systems
Jake Welde, Nishanth Rao, Pratik Kunapuli +2
Tracking controllers enable robotic systems to accurately follow planned reference trajectories. In particular, reinforcement learning (RL) has shown promise in the synthesis of co…
cs.RO2025
Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidance
Anish Bhattacharya, Nishanth Rao, Dhruv Parikh +5
We demonstrate the capabilities of an attention-based end-to-end approach for high-speed vision-based quadrotor obstacle avoidance in dense, cluttered environments, with comparison…