- Видео 56
- Просмотров 95 646
Autonomous Multi-Robots Lab Delft
Добавлен 29 авг 2014
The goal of the Autonomous Multi-Robots Laboratory at the Delft University of Technology, led by Prof. J. Alonso-Mora, is to develop novel methods for navigation, motion planning, learning and control of autonomous mobile robots, with a special emphasis on multi-robot systems, on-demand transportation and robots that interact with other robots and humans in dynamic and uncertain environments. Building towards the smart cities of the future, our applications include self-driving vehicles, mobile manipulators, micro-aerial vehicles, last-mile logistics and ride-sharing.
Particle-based Instance-aware Semantic Occupancy Mapping in Dynamic Environments
Particle-based Instance-aware Semantic Occupancy Mapping in Dynamic Environments. G. Chen, Z. Wang, W. Dong, J. Alonso-Mora. Accepted by IEEE T-RO, 2024.
Abstract: Representing the 3D environment with instance-aware semantic and geometric information is crucial for interaction-aware robots in dynamic environments. Nonetheless, creating such a representation poses challenges due to sensor noise, instance segmentation and tracking errors, and the objects' dynamic motion. This paper introduces a novel particle-based instance-aware semantic occupancy map to tackle these challenges. Particles with an augmented instance state are used to estimate the Probability Hypothesis Density (PHD) of the o...
Abstract: Representing the 3D environment with instance-aware semantic and geometric information is crucial for interaction-aware robots in dynamic environments. Nonetheless, creating such a representation poses challenges due to sensor noise, instance segmentation and tracking errors, and the objects' dynamic motion. This paper introduces a novel particle-based instance-aware semantic occupancy map to tackle these challenges. Particles with an augmented instance state are used to estimate the Probability Hypothesis Density (PHD) of the o...
Просмотров: 139
Видео
Dynamic Optimization Fabrics for Motion Generation
Просмотров 6421 день назад
Dynamic Optimization Fabrics for Motion Generation M. Spahn, M. Wisse, J. Alonso-Mora. In IIEEE Transactions on Robotics (T-RO), 2023. Optimization fabrics are a geometric approach to real-time local motion generation, where motions are designed by the composition of several differential equations that exhibit a desired motion behavior. We generalize this framework to dynamic scenarios and nonh...
Demonstrating Adaptive Mobile Manipulation in Retail Environments
Просмотров 16221 день назад
Demonstrating Adaptive Mobile Manipulation in Retail Environments Max Spahn, Corrado Pezzato, Chadi Salmi, Rick Dekker, Cong Wang, Christian Pek, Jens Kober, Javier Alonso-Mora, Carlos Hernández Corbato, Martijn Wisse. In , Proc. of Robotics: Science and Systems (RSS), 2024 Although autonomous robots have great potential to boost efficiency and throughput across the whole retail chain, they are...
Topology-Driven Parallel Trajectory Optimization in Dynamic Environments
Просмотров 4433 месяца назад
This video accompanies the paper "Topology-Driven Parallel Trajectory Optimization in Dynamic Environments" by O. de Groot, L. Ferranti, D. Gavrila, and J. Alonso-Mora. The authors are with the Dept. of Cognitive Robotics, TU Delft, 2628 CD Delft, The Netherlands. This work received support from the Dutch Science Foundation NWO-TTW, within the Veni project HARMONIA (18165), and the European Uni...
RSS 2024 Lab-tour demo - INTERACT
Просмотров 5396 месяцев назад
We are thrilled to demonstrate our latest research project on multi-mobile manipulators in a shared workspace during the RSS lab demos on Friday, 19th of July. #tudelft Project website: autonomousrobots.nl/projects/interact
Biased-MPPI: Informing Sampling-Based Model Predictive Control by Fusing Ancillary Controllers
Просмотров 4828 месяцев назад
Paper website: autonomousrobots.nl/paper_websites/biased-mppi
Multi-Robot Local Motion Planning using Dynamic Optimization Fabrics
Просмотров 555Год назад
In this paper, we address the problem of real-time motion planning for multiple robotic manipulators that operate in close proximity. We build upon the concept of dynamic fabrics and extend them to multi-robot systems, referred to as Multi-Robot Dynamic Fabrics (MRDF). This geometric method enables a very high planning frequency for high-dimensional systems at the expense of being reactive and ...
Planning among decision-making agents
Просмотров 850Год назад
Workshop talk at Intelligent Vehicles 2023
Visually-Guided Motion Planning for Autonomous Driving from Interactive Demonstrations
Просмотров 2872 года назад
R. Perez-Dattari, B. Brito, O. de Groot, J. Kober, and J. Alonso-Mora, "Visually-Guided Motion Planning for Autonomous Driving from Interactive Demonstrations", in IFAC Engineering Applications of Artificial Intelligence Journal, Nov. 2022. The successful integration of autonomous robots in real-world environments strongly depends on their ability to reason from context and take socially accept...
Distributed Nonlinear Trajectory Optimization for Multi-Robot Motion Planning
Просмотров 4832 года назад
This paper appears in: IEEE Transactions on Control Systems Technology Print ISSN: 1063-6536 Online ISSN: 1558-0865 Digital Object Identifier: 10.1109/TCST.2022.3211130 This work presents a method for multi-robot coordination based on a novel distributed nonlinear model predictive control (NMPC) formulation for trajectory optimization and its modified version to mitigate the effects of packet l...
Learning Interaction aware Guidance Policies for Motion Planning in Dense Traffic Scenarios
Просмотров 4312 года назад
B. Brito, A. Agarwal, J. Alonso-Mora, "Learning Interaction aware Guidance Policies for Motion Planning in Dense Traffic Scenarios", IEEE Transactions on Intelligent Transportation Systems, 2022
Improving Pedestrian Prediction Models with Self-Supervised Continual Learning
Просмотров 4572 года назад
Improving Pedestrian Prediction Models with Self-Supervised Continual Learning Luzia Knoedler, Chadi Salmi, Hai Zhu, Bruno Brito and Javier Alonso-Mora IEEE Int. Conferernce on Robotics and Automation, 2022 Autonomous mobile robots require accurate human motion predictions to safely and efficiently navigate among pedestrians, whose behavior may adapt to environmental changes. This paper introdu...
Where to Look Next: Learning Viewpoint Recommendations for Informative Trajectory Planning
Просмотров 5112 года назад
Max Lodel, Bruno Brito, Álvaro Serra-Gómez, Laura Ferranti, Robert Babuška, Javier Alonso-Mora Where to Look Next: Learning Viewpoint Recommendations for Informative Trajectory Planning IEEE Int. Conference on Robotics and Automation (ICRA) 2022 Search missions require motion planning and navigation methods for information gathering that continuously replan based on new observations of the robo...
Regulations Aware Motion Planning for Autonomous Surface Vessels in Urban Canals
Просмотров 3512 года назад
Jitske de Vries, Elia Trevisan, Jules van der Toorn, Tuhin Das, Bruno Brito, Javier Alonso-Mora Regulations Aware Motion Planning for Autonomous Surface Vessels in Urban Canals IEEE Int. Conference on Robotics and Automation (ICRA) 2022 In unstructured urban canals, regulation-aware interactions with other vessels are essential for collision avoidance and social compliance. In this paper, we pr...
Decentralized Probabilistic Multi-Robot Collision Avoidance
Просмотров 9343 года назад
Decentralized Probabilistic Multi-Robot Collision Avoidance Using Buffered Uncertainty-Aware Voronoi Cells, by H. Zhu, B. Brito and J. Alonso-Mora, Autonomous Robots, 2021. DOI: 10.1007/s10514-021-10029-2 In this paper, we present a decentralized and communication-free collision avoidance approach for multi-robot systems that accounts for both robot localization and sensing uncertainties. The a...
Curvature Aware Motion Planning with Closed-Loop Rapidly-exploring Random Trees
Просмотров 4173 года назад
Curvature Aware Motion Planning with Closed-Loop Rapidly-exploring Random Trees
Coupled mobile manipulation via trajectory optimization with free space decomposition
Просмотров 4763 года назад
Coupled mobile manipulation via trajectory optimization with free space decomposition
Where to go next: Learning a Subgoal Recommendation Policy for Navigation in Dynamic Environments
Просмотров 8013 года назад
Where to go next: Learning a Subgoal Recommendation Policy for Navigation in Dynamic Environments
Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning
Просмотров 1,3 тыс.3 года назад
Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning
Robust Vision-based Obstacle Avoidance for Micro Aerial Vehicles in Dynamic Environments - Hai Zhu
Просмотров 2,1 тыс.4 года назад
Robust Vision-based Obstacle Avoidance for Micro Aerial Vehicles in Dynamic Environments - Hai Zhu
Anticipatory Vehicle Routing for Same-Day Pick-up and Delivery using Historical Data Clustering
Просмотров 5204 года назад
Anticipatory Vehicle Routing for Same-Day Pick-up and Delivery using Historical Data Clustering
Learning Efficient Communication for Multi-Robot Collision Avoidance - Alvaro Serra
Просмотров 3034 года назад
Learning Efficient Communication for Multi-Robot Collision Avoidance - Alvaro Serra
With Whom to Communicate: Learning Efficient Communication for Multi-Robot Collision Avoidance
Просмотров 3144 года назад
With Whom to Communicate: Learning Efficient Communication for Multi-Robot Collision Avoidance
Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Interacting Pedestrians
Просмотров 1,5 тыс.4 года назад
Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Interacting Pedestrians
Online Trajectory Planning and Control of a MAV Payload System in Dynamic Environments
Просмотров 7204 года назад
Online Trajectory Planning and Control of a MAV Payload System in Dynamic Environments
Robust Vision-based Obstacle Avoidance for Micro Aerial Vehicles in Dynamic Environments
Просмотров 3,3 тыс.4 года назад
Robust Vision-based Obstacle Avoidance for Micro Aerial Vehicles in Dynamic Environments
Presentation B-UAVC for Probabilistic Multi-Robot Collision Avoidance
Просмотров 2475 лет назад
Presentation B-UAVC for Probabilistic Multi-Robot Collision Avoidance
Social behavior for autonomous vehicles
Просмотров 3155 лет назад
Social behavior for autonomous vehicles
B-UAVC: Buffered Uncertainty-Aware Voronoi Cells for Probabilistic Multi-Robot Collision Avoidance
Просмотров 2775 лет назад
B-UAVC: Buffered Uncertainty-Aware Voronoi Cells for Probabilistic Multi-Robot Collision Avoidance
SafeVRU: A Research Platform for the Interaction of Self-Driving Vehicles with Vulnerable Road Users
Просмотров 1255 лет назад
SafeVRU: A Research Platform for the Interaction of Self-Driving Vehicles with Vulnerable Road Users
Ms. Zamani wonderful job👏👏
What a wonderful study! I am currently a fourth-year student, and I am also conducting a scientific research project on obstacle avoidance algorithms for drones. May I contact you to discuss this research a bit further?"
Have you uploaded it to GitHub?
very interesting thank you for sharing
Hello ! i am a student in VIT and wanted to know how these swarm robots or drones can work ? can you help me with these ?
Dr. Alonso-Mora, you and your team have done it again!
Really Cool! Can you share the repository
fine result! Do you have a github repo of your code?
3:45 That looks quite dangerous)
Excellent Work. At 3:44 you probably have a typo replacing "Unstructured" with "Unconstrained" in the title.
Hi, is the code for this paper open source?
Hello Professor, Recently, I’m learning multi-robots self-organizing cooperative pursuit algorithm based on Voronoi graph. but I have encountered some troubles when trying to implement the Buffered Voronoi Cells algorithm. If possible, can you send me your Buffered Voronoi Cells part source code or pseudocode?
Yes: paper: www.alonsomora.com/docs/19-brito-ral.pdf code: github.com/tud-amr/amr-lmpcc
Can it build on ubuntu 18.04 melodic?
Can you share the lmpcc local planner imformation? and how to use it
How can I contact you
Is this paper code open source?
Super great job👍
Hi, professor. I am a junior student and currently trying to integrate the methods you proposed in this paper to real-world ride-sharing problems. One obstacle I met is that it's quite hard to solve the optimal assignment problem because it is an integer programming problem and using a solver to solve it requires a lot of time. Do you think there might be some ways to just use a linear programming solver to solve it?
Hi, you can solve a real valued LP if you only assign one request per vehicle in each time-step (vehicles may have passengers onboard). Otherwise, you need to solve the ILP.
@@amrlab Thank you for replying, professor. Assume we are only thinging about the assignment problem at a particular time (the algorithm 3 in the paper). Even if we assign one request for each car, the problem still contains integer constraints (for ex. \epsilon_{i,j}), and an integer programming solver is stilled needed. I wonder if I misunderstand something.
你好 这个代码可以分享吗
Hi, Does Bebop 2 itself support intel realsense D435i?
Dr. Alonso-Mora, how do we get a hold of you?
splendid work by you!!
I would love some explanation on figure1 :)
Are you using the motion capture system in the robots motion planning or in the pose estimation ?
hello Professor, I am very interested in your research and want to continue it.Can I refer to your source code ?How can i get your source code? 1263305115@qq.com
This is amazing! can't wait to read the paper! well done!
do you know how to find this paper?
the value of "travel distance, c.m." is supposed to be a mean value for current 30 second period, measured in "km/vehicle" but it keeps increasing steadily throughout the first part of the video from 0 to 367. Clearly this can not be the mean km / vehicle in the last 30 seconds. What does the value measure? Mean km / vehicle since beginning of video?
WOW!
Hello, does anyone know how to get the number of active taxis? I am using www.nyc.gov/html/tlc/html/about/trip_record_data.shtml.
So, what's the drones equipped with?
Nice! Could use some work at the jitter, but really cool to see the amount of tracking that is possible ;)
Can I have the code and other useful stuff for some more study on this topic?
I have a question (well several, but I'll make just one ... for now :D), how did you create the trajectory?
This is awesome. May I have the code for this ? It doesn't seem like you used ROS for this simulation. Was it Matlab ?
can i get matlab simulation?
can i get matlab simulation for this project.
Would be interesting to take Uber driver data and use as a "collective experience set" for autonomous / AI driving robots making the decisions processes a touch more human / organic. (I'm like a 3rd grader talking to a professor here haha)
The ability to select the target and choose a camera angle on that target, and then to watch the drone execute that change in 3D space, in time, and repositioning is amazing. AAAANNNDD tracking of multiple objects with the variable position changes and the "choices" it's making are on such another level! Dream team in action. Crazy tech. I feel like I'm witnessing a necessary milestone in AI. Amazing job guys.
Having no solid understanding of the tech behind your obstacle recognition systems (sensors / cameras etc) I wonder how light field technology might benefit (or not) as an alternative method of spatially mapping obstacles.
It's great. Could it possible for me to have your code behind? Thanks
I've been studying multi-robot formation control. Your work is amazing. Wondering if you have plan to open source the project.
My understanding is that this model is using real historical NYC taxi trips; but all the trips seem to begin and end in Manhattan. So other taxi trips (that didn't both begin and end in Manhattan) were excluded from the data used in the simulation?
Yes, we use real NYC taxi data, which is mostly from Manhattan. Indeed, we only considered trips which start and end in Manhattan. The method could be applied to the larger NYC or other cities.
If you had included all trips, how much would the trips going outside of Manhattan decrease your efficiency?
Can you please share how did you clean the data outside of Manhattan ?
Hello, do you mind telling me that how you know the number of active taxis is 13,586 (In you paper On-demand high-capacity ride-sharing via dynamic trip-vehicle assignment)?
As your video stands at the point I was unable to make out at all what you are trying to say. It would of helped me understand if you added a voice over tell the viewer what we are looking at and how the color dots moving very fast is related to On-demand High-capacity Ride-sharing.
Good point. In the video we run our algorithm to route a fleet of taxis, which serve real requests from Manhattan. Each dot represents one vehicle and its color the number of passengers at that time instance. The dots move as the vehicles move through-out a day of activity. We highlight the path of two vehicles, with pick-ups and drop-offs. The video shows: - How the algorithm works - A comparison for three fleet sizes and for three capacities and for the different days of the week.
what application did you use to make simulation?
C++/python with ROS for the robots, matlab for the simulations