Ensuring safe, real-time motion planning in arbitrary environments requires a robotic manipulator to avoid collisions, obey joint limits, and account for uncertainties in the mass and inertia of objects and the robot itself. This paper proposes Autonomous Robust Manipulation via Optimization with Uncertainty-aware Reachability (ARMOUR), a provably-safe, receding-horizon trajectory planner and tracking controller framework for robotic manipulators to address these challenges. ARMOUR first constructs a robust controller that tracks desired trajectories with bounded error despite uncertain dynamics. ARMOUR then uses a novel recursive Newton-Euler method to compute all inputs required to track any trajectory within a continuum of desired trajectories. Finally, ARMOUR over-approximates the swept volume of the manipulator; this enables one to formulate an optimization problem that can be solved in real-time to synthesize provably-safe motions. This paper compares ARMOUR to state of the art methods on a set of challenging manipulation examples in simulation and demonstrates its ability to ensure safety on real hardware in the presence of model uncertainty without sacrificing performance. Project page: https://roahmlab.github.io/armour/.

Differentially Private (DP) learning has seen limited success for building large deep learning models of text, and straightforward attempts at applying Differentially Private Stochastic Gradient Descent (DP-SGD) to NLP tasks have resulted in large performance drops and high computational overhead. We show that this performance drop can be mitigated with (1) the use of large pretrained language models; (2) non-standard hyperparameters that suit DP optimization; and (3) fine-tuning objectives which are aligned with the pretraining procedure. With the above, we obtain NLP models that outperform state-of-the-art DP-trained models under the same privacy budget and strong non-private baselines -- by directly fine-tuning pretrained models with DP optimization on moderately-sized corpora. To address the computational challenge of running DP-SGD with large Transformers, we propose a memory saving technique that allows clipping in DP-SGD to run without instantiating per-example gradients for any linear layer in the model. The technique enables privately training Transformers with almost the same memory cost as non-private training at a modest run-time overhead. Contrary to conventional wisdom that DP optimization fails at learning high-dimensional models (due to noise that scales with dimension) empirical results reveal that private learning with pretrained language models doesn't tend to suffer from dimension-dependent performance degradation. Code to reproduce results can be found at https://github.com/lxuechen/private-transformers.

In this tutorial, you will create an automatic Sudoku puzzle solver using OpenCV, Deep Learning, and Optical Character Recognition (OCR). My wife is a huge Sudoku nerd. Every time we travel, whether it be a 45-minute flight from Philadelphia to Albany or a 6-hour transcontinental flight to California, she always has a Sudoku puzzle with her. The funny thing is, she prefers the printed Sudoku puzzle books. She hates the digital/smartphone app versions and refuses to play them. I'm not a big puzzle person myself, but one time, we were sitting on a flight, and I asked: How do you know if you solved the puzzle correctly?

Founded in 2015, Agility Robotics is developing highly capable bipedal robots for a range of different uses – such as last-mile logistics, telepresence, automated inspection, entertainment, and academic research. By supplying legged machines that can go anywhere a person can go, Agility aims to create a dramatic new mobility option to automate applications never before thought possible. The company, based in Albany, Oregon, USA, has just revealed the latest iteration of its'Digit' robot. This machine (version 2.0) now features a ground-up torso redesign, a foot with two degrees of freedom, active cooling and expanded environmental range, a larger battery, and improved perception. In the video below, Digit can be seen demonstrating shared autonomy, with picking/placing and footstep placement using a combination of autonomous navigation while under local teleoperation.

Robots have walked on legs for decades. Today's most advanced humanoid robots can tramp along flat and inclined surfaces, climb up and down stairs, and slog through rough terrain. But despite the progress, legged robots still can't begin to match the agility, efficiency, and robustness of humans and animals. Existing walking robots hog power and spend too much time in the shop. All too often, they fail, they fall, and they break. For the robotic helpers we've long dreamed of to become a reality, these machines will have to learn to walk as we do. We must build robots with legs because our world is designed for legs.

Today, Agility Robotics is announcing US $8 million in Series A funding "to accelerate product, technology, and business development." Leading the round is Playground Global, founded by Android co-creator and ex-Google Robotics head Andy Rubin, and also joining in is Sony Innovation Fund. We don't write about funding rounds all that often, but this could be the first robotics company to get such a significant amount of VC funding to develop a realistic commercial bipedal robot. There are certainly other well-funded companies working on bipeds, including Boston Dynamics and Schaft. But while it's not that clear what commercial applications these companies are targeting, Agility Robotics is very specifically and deliberately working on a legged robot that can make deliveries.