8 papers
Battery-Aware Reinforcement Learning for Aggressive Quadrotor Flight
Alejandro Sanchez Roncero, Olov Andersson, Petter Ogren
Agile flight tasks such as drone racing and pursuit-evasion require strong acceleration and precise turns, but the available thrust changes as the battery discharges and voltage dr…
TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation
Qingwen Zhang, Chenhan Jiang, Xiaomeng Zhu +4
Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks…
Learning to Localize Reference Trajectories in Image-Space for Visual Navigation
Finn Lukas Busch, Matti Vahs, Quantao Yang +4
We present LoTIS, a model for visual navigation that provides robot-agnostic image-space guidance by localizing a reference RGB trajectory in the robot's current view, without requ…
DIV-Nav: Open-Vocabulary Spatial Relationships for Multi-Object Navigation
Jesús Ortega-Peimbert, Finn Lukas Busch, Timon Homberger +2
Advances in open-vocabulary semantic mapping and object navigation have enabled robots to perform an informed search of their environment for an arbitrary object. However, such zer…
Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games
Alejandro Sanchez Roncero, Yixi Cai, Olov Andersson +1
In this letter we study 1v1 quadrotor pursuit-evasion, where a pursuer and an evader are trained via reinforcement learning (RL) by competing against each other. Such adversarial s…
ViSA-Flow: Accelerating Robot Skill Learning via Large-Scale Video Semantic Action Flow
Changhe Chen, Quantao Yang, Xiaohao Xu +2
One of the central challenges preventing robots from acquiring complex manipulation skills is the prohibitive cost of collecting large-scale robot demonstrations. In contrast, huma…
FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions
Daniel Marta, Simon Holk, Miguel Vasco +6
Preference-based reinforcement learning (PbRL) is a suitable approach for style adaptation of pre-trained robotic behavior: adapting the robot's policy to follow human user prefere…
One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigation
Finn Lukas Busch, Timon Homberger, Jesús Ortega-Peimbert +2
The capability to efficiently search for objects in complex environments is fundamental for many real-world robot applications. Recent advances in open-vocabulary vision models hav…