Visually-guided motion planning for autonomous driving from interactive demonstrations

Pérez-Dattari, Rodrigo; Brito, Bruno; Groot, Oscar de; Kober, Jens; Alonso–Mora, Javier

doi:10.1016/j.engappai.2022.105277

Cited by 7 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, regarding works related to automated systems in the passenger transportation domain, several studies focus on autonomous vehicles 36 – 38 , transportation within smart cities 39 – 41 , and the impacts of mobility services 42 , 43 , among other things. Specifically in relation to the use of artificial agents in passenger transportation, studies have simulated information availability 44 , optimized passenger evacuation optimization in metro stations 45 , and simulated passenger boarding and alighting spatially confined transportation scenarios 46 .…”

Section: Literature Reviewmentioning

confidence: 99%

Bio-inspired artificial somatic index for reflecting the travel experience of passenger agents under a flexible transportation scenario

Cabrera-Paniagua,

Flores,

Rubilar-Torrealba

et al. 2023

Sci Rep

View full text Add to dashboard Cite

This work analyzes the implementation of an artificial mechanism inspired by a biological somatic marker that ables a passenger agent to both, react to changes in the service, as well as keep said reactions as a memory for future decisions. An artificial mental model was designed, and the passenger agent was implemented as an autonomous decision-making system, where both, the choice of the transport operator and the evaluation of the received service were fully delegated to the system. The evaluation of the service experience is not only based on rational aspects (such as the cost of the trip) but also on subjective aspects related to the satisfaction level derived from the passenger's experience. The experimental scenario considered 10,000 trip requests simulated within an artificial map that emulates characteristics that are usually present in a city, such as vehicular congestion, the unsafety of certain streets, or the benefits of an area with tourist interest. The results show that the option to travel under a transport operator with a touristic profile is a trend. Unlike current cases in the industry, this research work explores the scenario where the passenger can have as a client a trip profile with memory, differentiated from other clients, and can receive more than one trip proposal for the same trip request, according to the different conditions that the passenger is looking for.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Bio-inspired artificial somatic index for reflecting the travel experience of passenger agents under a flexible transportation scenario

Cabrera-Paniagua,

Flores,

Rubilar-Torrealba

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Autonomous Driving Autonomous driving is a challenging robotics problem due to varying environments, terrain, topologies and dynamic vehicle/pedestrian interaction or disturbances. This area of research aims to develop intelligent autonomous vehicles to achieve safe and high-performance mobility (Pérez-Dattari et al, 2022). The problem consists of steering the vehicle based on sensory observations (camera, radar, lidar etc.)…”

Section: Navigationmentioning

confidence: 99%

Interactive Imitation Learning in Robotics: A Survey

Celemin¹,

Pérez-Dattari²,

Chisari³

et al. 2022

Preprint

View full text Add to dashboard Cite

Interactive Imitation Learning (IIL) is a branch of Imitation Learning (IL) where human feedback is provided intermittently during robot execution allowing an online improvement of the robot's behavior.In recent years, IIL has increasingly started to carve out its own space as a promising data-driven alternative for solving complex robotic tasks. The advantages of IIL are twofold, 1) it is data-efficient, as the human feedback guides the robot directly towards an improved behavior (in contrast with Reinforcement Learning (RL), where behaviors must be discovered by trial and error), and 2) it is robust, as the distribution mismatch between the teacher and learner trajectories is minimized by providing feedback directly over the learner's trajectories (as opposed to offline IL methods such as Behavioral Cloning).Nevertheless, despite the opportunities that IIL presents, its terminology, structure, and applicability are not clear nor unified in the literature, slowing down its development and, therefore, the research of innovative formulations and discoveries.In this article, we attempt to facilitate research in IIL and lower entry barriers for new practitioners by providing a survey of the field that unifies and structures it. In addition, we aim to raise awareness of its potential, what has been accomplished and what are still open research questions.

show abstract

Long Short‐Term Memory‐Based Multi‐Robot Trajectory Planning: Learn from MPCC and Make It Better

Xin,

Xu,

Zhu

et al. 2024

Advanced Intelligent Systems

View full text Add to dashboard Cite

The current trajectory planning methods for multi‐robot systems face challenges due to high computational burden and inadequate adaptability in complex constrained environments, obstructing efficiency improvements in production and logistics. This article presents an innovative solution by integrating model predictive contouring control (MPCC) and long short‐term memory (LSTM) networks for real‐time trajectory planning of multiple mobile robots. Based on the datasets generated by MPCC, a customized LSTM network is constructed to learn the collaborative planning behavior from these datasets offline, subsequently producing smooth and efficient trajectories online with a low computational burden. Moreover, a hybrid control scheme, incorporating a lidar‐based safety evaluator, avoids unexpected collision risks by switching to MPCC when necessary, ensuring the overall safety and reliability of the multi‐robot system. The proposed hybrid LSTM method is implemented and tested in the robot operating system (ROS) within diverse constrained scenarios. Experimental results demonstrate that the hybrid LSTM method achieves ≈6% enhancements in trajectory productivity and a reduced computational burden of roughly 75% compared to MPCC, thereby providing a promising solution for local multi‐robot trajectory planning in logistics transportation tasks.

show abstract

Visually-guided motion planning for autonomous driving from interactive demonstrations

Cited by 7 publications

References 27 publications

Bio-inspired artificial somatic index for reflecting the travel experience of passenger agents under a flexible transportation scenario

Bio-inspired artificial somatic index for reflecting the travel experience of passenger agents under a flexible transportation scenario

Interactive Imitation Learning in Robotics: A Survey

Long Short‐Term Memory‐Based Multi‐Robot Trajectory Planning: Learn from MPCC and Make It Better

Contact Info

Product

Resources

About