Update webpage

mkdocs.yml

@@ -9,6 +9,7 @@ nav:
   - News: news.md
   - Publications: publications.md
   - Contact: contact.md
+  - RobotDART: robot_dart
   # - Videos: videos.md
 
 theme:
@@ -57,6 +58,9 @@ extra:
     - icon: fontawesome/brands/github
       link: https://github.com/NOSALRO
       name: NOSALRO on GitHub
+    - icon: fontawesome/brands/linkedin-in
+      link: https://www.linkedin.com/in/nosalro-project-13194a273/
+      name: NOSALRO on LinkedIn
     - icon: fontawesome/brands/youtube
       link: https://www.youtube.com/@nosalro
       name: NOSALRO on YouTube

src/news.md

@@ -3,6 +3,10 @@
     -navigation
 ---
 
+## 22th April 2024
+
+Our short paper **"Effective Kinodynamic Planning and Exploration through Quality Diversity and Trajectory Optimization"** by *Asimakopoulos, K., Androutsopoulos, A., Vrahatis, M. and Chatzilygeroudis, K.* has been accepted for presentation at the *international conference [LION18](https://www.lion18.unina.it/)*. More information on our paper [here](publications.md). The following presentation-only abstracts have been accepted as well: 1) **"Effective Skill Learning via Autonomous Goal Representation Learning"** by *C. Tsakonas and K. Chatzilygeroudis*, and 2) **"Evolving Dynamic Locomotion Policies in Minutes"** by *K. Chatzilygeroudis, C. Tsakonas and M. Vrahatis*! See you at Ischia in June 2024!
+
 ## 15th June 2023
 
 We are delighted to share that we have two papers accepted at The Fourteenth International Conference on Information, Intelligence, Systems and Applications ([IISA 2023](https://easyconferences.eu/iisa2023/))! At IISA 2023, we will be presenting **"Effective Skill Learning via Autonomous Goal Representation Learning"** by *C. Tsakonas and K. Chatzilygeroudis* and **"Evolving Dynamic Locomotion Policies in Minutes"** by *K. Chatzilygeroudis, C. Tsakonas and M. Vrahatis*. More information on our papers [here](publications.md). See you at Volos in July!

src/publications.md

@@ -5,14 +5,24 @@
 
 ## International Conferences
 
+### 4. Asimakopoulos, K., Androutsopoulos, A., Vrahatis, M. and Chatzilygeroudis, K. 2024. **Effective Kinodynamic Planning and Exploration through Quality Diversity and Trajectory Optimization**. *The 18th learning and intelligent optimization conference (LION).*
+
+   **Abstract:** *Efficient and rapid kinodynamic planning is crucial for numerous real-world robotics applications. Various methods have been proposed to address this challenge, primarily falling into two categories: (a) randomized planners and (b) trajectory optimization utilizing simplified models and numerical optimization. Randomized planners such as RRT and PRM excel in exploring the state space, while trajectory optimization methods, like direct collocation, are adept at discovering optimal trajectories within well-defined spaces. We aim to achieve effective and efficient kinodynamic planning and exploration by integrating evolutionary algorithms (Quality-Diversity) with trajectory optimization. Our preliminary experiments showcase that using the proposed methodology we get the best from both worlds on two simulated experiments.*
+
+   [(view online)](https://costashatz.github.io/files/LION18.pdf)
+
 ### 3. Tsakonas, C. and Chatzilygeroudis, K. 2023. **Effective Skill Learning via Autonomous Goal Representation Learning**. *The Fourteenth International Conference on Information, Intelligence, Systems and Applications (IISA 2023)*
 
    **Abstract:** *A long standing goal of robotics researchers is to develop robots that are able to develop in an autonomous open-ended manner through lifelong learning and interactions. If we are to see robots learning in an autonomous and open-ended manner, we need to develop methods for incremental and autonomous skill discovery and trial-and-error learning. In other words, we want our robots to be able to autonomously select their goals according to their current capabilities and learn controllers or policies to achieve those goals. In this paper, we take a step towards solving this challenge and propose a novel pipeline, called AGRL, that effectively combines deterministic simulations, Variational Auto-Encoders (VAEs) and Reinforcement Learning (RL) and enables robots to learn goal-conditioned policies suited to their capabilities. Our main intuition is that we can use effective exploration strategies in order to learn a good goal representation and distribution, and then use this distribution to generate effective and reachable goals for fast skill learning. We extensively evaluate the proposed method in simulation with a 7DOF manipulator and a differential drive mobile robot.*
 
+   [(view online)](https://costashatz.github.io/files/IISA2023-AGRL.pdf) [(video)](https://www.youtube.com/watch?v=x-j5mid6jxM)
+
 ### 2. Chatzilygeroudis, K., Tsakonas, C. and Vrahatis, M. 2023. **Evolving Dynamic Locomotion Policies in Minutes**. *The Fourteenth International Conference on Information, Intelligence, Systems and Applications (IISA 2023)*
 
    **Abstract:** *Many effective evolutionary methods have been proposed that allow robots to learn how to walk. Most of the proposed methods have one or more of the following drawbacks: (a) utilization of hand designed open loop policies that cannot scale to different robots, and/or (b) requiring big wall time due to sample inefficiency and simulation costs, a fact that limits the practical usage of those algorithms. In the paper at hand, we propose combination of (a) a simplified model for locomotion dynamics, and (b) the effectiveness of quality-diversity algorithms, and propose a novel algorithm that is able to evolve, in less than an hour on a standard computer, generic (e.g. neural network), and reactive locomotion policies. Our approach makes it possible to generate in a few minutes reactive policies for locomotion that can perform dynamic motions like jumps. We also present preliminary results of transferring the behaviors to realistic simulators using a whole body inverse kinematics solver and a joint impedance controller.*
 
+   [(view online)](https://costashatz.github.io/files/IISA2023-EvoLoco.pdf) [(video)](https://www.youtube.com/watch?v=VdyUlAAWMzQ)
+
 ### 1. Chatzilygeroudis, K. and Vrahatis, M. 2023. **Fast and Robust Constrained Optimization via Evolutionary and Quadratic Programming**. *The 17th learning and intelligent optimization conference (LION).*
 
    **Abstract:** *Many efficient and effective approaches have been proposed in the evolutionary computation literature for solving constrained optimization problems. Most of the approaches assume that both the objective function and the constraints are black-box functions, while a few of them can take advantage of the gradient information. On the other hand, when the gradient information is available, the most versatile approaches are arguably the ones coming from the numerical optimization literature. Perhaps the most popular methods in this field are sequential quadratic programming and interior point. Despite their success, those methods require accurate gradients and usually require a well-shaped initialization to work as expected. In the paper at hand, a novel hybrid method, named UPSO-QP, is presented that is based on particle swarm optimization and borrows ideas from the numerical optimization literature and sequential quadratic programming approaches. The proposed method is evaluated on numerous constrained optimization tasks from simple low dimensional problems to high dimensional realistic trajectory optimization scenarios, and showcase that is able to outperform other evolutionary algorithms both in terms of convergence speed as well as performance, while also being robust to noisy gradients and bad initialization.*

src/team.md

@@ -31,13 +31,13 @@
 
 **Website:** [https://github.com/konassimako](https://github.com/konassimako)
 
-## Konstantinos Tsinganos
+<!-- ## Konstantinos Tsinganos
 
 ![Konstantinos Tsinganos](images/kt.jpg){: style="width:10%"}
 
 **Short bio:** Konstantinos Tsinganos received his diploma (Integrated Master) in Electrical and Computer Engineering from the University of Patras, Greece in 2019 with an expertise in computer software and digital image processing. Following his undergraduate studies, he enrolled for the postgraduate program "Data-driven Computing and Decision Making" at the Department of Computer Engineering and Informatics (CEID), University of Patras, Greece where he obtained a Master of Science degree in 2021. During his postgraduate studies, he supported as teaching assistant the undergraduate courses of databases, object-oriented programming and intelligent systems and robotics. Currently, he is a first year PhD student at CEID pursuing research on Sim2Real methods for visual-based imitation learning. His research interests include robot learning, computer vision and machine learning. In addition to his academic studies, he is a software engineer at Metargus startup located in Patras, Greece where he is responsible for implementing computer vision and video processing pipelines for basketball game events.
 
-**Website:** [https://kostastsing.github.io](https://kostastsing.github.io)
+**Website:** [https://kostastsing.github.io](https://kostastsing.github.io) -->
 
 # Advisory Board