High Power Laser (HPL) systems operate in the femtosecond regime--one of the shortest timescales achievable in experimental physics. HPL systems are instrumental in high-energy physics, leveraging ultra-short impulse durations to yield extremely high intensities, which are essential for both practical applications and theoretical advancements in light-matter interactions. Traditionally, the parameters regulating HPL optical performance are tuned manually by human experts, or optimized by using black-box methods that can be computationally demanding. Critically, black box methods rely on stationarity assumptions overlooking complex dynamics in high-energy physics and day-to-day changes in real-world experimental settings, and thus need to be often restarted. Deep Reinforcement Learning (DRL) offers a promising alternative by enabling sequential decision making in non-static settings. This work investigates the safe application of DRL to HPL systems, and extends the current research by (1) learning a control policy directly from images and (2) addressing the need for generalization across diverse dynamics. We evaluate our method across various configurations and observe that DRL effectively enables cross-domain adaptability, coping with dynamics' fluctuations while achieving 90% of the target intensity in test environments.

Varying dynamics parameters in simulation is a popular Domain Randomization (DR) approach for overcoming the reality gap in Reinforcement Learning (RL). Nevertheless, DR heavily hinges on the choice of the sampling distribution of the dynamics parameters, since high variability is crucial to regularize the agent's behavior but notoriously leads to overly conservative policies when randomizing excessively. In this paper, we propose a novel approach to address sim-to-real transfer, which automatically shapes dynamics distributions during training in simulation without requiring real-world data. We introduce DOmain RAndomization via Entropy MaximizatiON (DORAEMON), a constrained optimization problem that directly maximizes the entropy of the training distribution while retaining generalization capabilities. In achieving this, DORAEMON gradually increases the diversity of sampled dynamics parameters as long as the probability of success of the current policy is sufficiently high. We empirically validate the consistent benefits of DORAEMON in obtaining highly adaptive and generalizable policies, i.e. solving the task at hand across the widest range of dynamics parameters, as opposed to representative baselines from the DR literature. Notably, we also demonstrate the Sim2Real applicability of DORAEMON through its successful zero-shot transfer in a robotic manipulation setup under unknown real-world parameters.

There is an episode of Doraemon where the robotic cat uses a wand to get products shown on the TV. The latest toy, that new dress – anything a person wanted could be obtained by pointing the wand at the object displayed on the screen. New York-based retailer Choosy is like Doraemon's gadget for womenswear. Imagine scrolling through Instagram and seeing an outfit that you like. Up until now, you tap the photo and see if the brands are tagged.

Rex Sham and his WALL-E-inspired robots are improving fire detection to slash carbon emissions and make the world better. If he were in a movie, Rex Sham would be the bad guy, or at the very least the well-meaning scientist who unwittingly wipes out the human race. In reality, Sham, the co-founder and chief science officer of Insight Robotics, is using his ingenious, WALL-E-like fire-detecting robots to save the planet. What Sham has developed is an automated early warning system that combines a high-precision, pan-tilt robot with thermal imaging sensors and advanced artificial intelligence (AI) vision technology. In its tests of the Computer Vision Wildfire Detection System, the Guangdong Academy of Forestry (Insight Robotics' research partner since 2010) has recorded a 100 per cent detection rate in multiple field trials and deployments.

With yet another big Doraemon movie set for release this March, Bandai Namco has unveiled a new Doraemon themed virtual reality, or VR, experience to tie in with the film. If you are somehow unfamiliar with the phenomenon of Doraemon it started as a manga at the end of the 60's penned by Fujiko Fujio. The premise had a robotic cat called Doraemon from the 22nd century sent back in time to improve the fortunes of the Nobi family due to the prior failings of Nobita Nobi. Doraemon's mission then was to aid Nobita in the past but in typical fashion, the variety of Doraemon's future gadgetry often ended up making things worse but at the very least everybody had a great deal of fun while doing so. What's amazing about Doraemon as a series is that it has lost none of its vitality over the years.