Dynamic obstacle avoidance is a popular research topic for autonomous systems, such as micro aerial vehicles and service robots. Accurately evaluating the performance of dynamic obstacle avoidance methods necessitates the establishment of a metric to quantify the environment's difficulty, a crucial aspect that remains unexplored. In this paper, we propose four metrics to measure the difficulty of dynamic environments. These metrics aim to comprehensively capture the influence of obstacles' number, size, velocity, and other factors on the difficulty. We compare the proposed metrics with existing static environment difficulty metrics and validate them through over 1.5 million trials in a customized simulator. This simulator excludes the effects of perception and control errors and supports different motion and gaze planners for obstacle avoidance. The results indicate that the survivability metric outperforms and establishes a monotonic relationship between the success rate, with a Spearman's Rank Correlation Coefficient (SRCC) of over 0.9. Specifically, for every planner, lower survivability leads to a higher success rate. This metric not only facilitates fair and comprehensive benchmarking but also provides insights for refining collision avoidance methods, thereby furthering the evolution of autonomous systems in dynamic environments.

Backdoor attacks have been one of the emerging security threats to deep neural networks (DNNs), leading to serious consequences. One of the mainstream backdoor defenses is model reconstruction-based. Such defenses adopt model unlearning or pruning to eliminate backdoors. However, little attention has been paid to survive from such defenses. To bridge the gap, we propose Venom, the first generic backdoor attack enhancer to improve the survivability of existing backdoor attacks against model reconstruction-based defenses. We formalize Venom as a binary-task optimization problem. The first is the original backdoor attack task to preserve the original attack capability, while the second is the attack enhancement task to improve the attack survivability. To realize the second task, we propose attention imitation loss to force the decision path of poisoned samples in backdoored models to couple with the crucial decision path of benign samples, which makes backdoors difficult to eliminate. Our extensive evaluation on two DNNs and three datasets has demonstrated that Venom significantly improves the survivability of eight state-of-the-art attacks against eight state-of-the-art defenses without impacting the capability of the original attacks.

I recently started an AI-focused educational newsletter, that already has over 125,000 subscribers. TheSequence is a no-BS (meaning no hype, no news etc) ML-oriented newsletter that takes 5 minutes to read. The goal is to keep you up to date with machine learning projects, research papers and concepts. The emergence of trends such as self-driving cars or drones has helped to popularize an area of artificial intelligence(AI) research known as autonomous agents. Conceptually, autonomous agents are AI that builds knowledge in real-time based on the characteristics of their surrounding environment as well as other agents.

In the previous post, we discussed six little-known challenges after deploying machine learning. This follow-up will share some practices I've found useful to maintaining machine learning in production. With close to 20 suggestions, it can get overwhelming. Fret not, I'll highlight the top three must-haves and good-to-haves at the end of this post. We'll go through some practical tools to help with maintaining machine learning in prod. "Data is the New Oil." "Garbage in, Garbage Out." These clichés emphasize that clean input data is essential to your system.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Senior Air Force commanders are employing new tactics, technologies and protocols to better safeguard drones from being shot down by enemy fire during missions. Air Force Gen. Jeffrey Harrigian, the commander of U.S. Forces Europe, recently told reporters that senior U.S. military leaders are now in an effort to increase mission survivability for combat drones operating in high-risk areas. Responding to a question about an MQ-9 Reaper being shot down over Yemen last year, Harrigian emphasized that drone operations need to become less predictable to enemies. "There is something to be said for operating in a manner that offers us an opportunity to not be as predictable as we have been.

Autonomous agents, such as self-driving cars and drones, need to make decisions in real time, which is particularly important but difficult in critical situations for example to avoid collisions. Such decisions often need to be made in a sequential manner to achieve the eventual goal (e.g., avoiding collisions and recovering to safe conditions), under partially observable environment, and by taking into account how other agents behave. Towards this far-reaching goal of realizing such autonomous agents, we propose practical techniques of sequential decision making in real time and demonstrate their effectiveness in Pommerman, a multi-agent environment that has been used in one of the competitions held at the Thirty-second Conference on Neural Information Processing Systems (NeurIPS 2018) on Dec. 8, 2018 Resnick et al. [2018a]. The techniques that we propose in this paper have been used in the Pommerman agents (HakozakiJunctions and dypm-final) who have won the first and third places in the competition. In Pommerman, a team of two agents competes against another team of two agents on a board of 11 11 grids (see Figure 1 (a) for an initial configuration of the board). Each agent can observe only a limited area of the board, and the agents cannot communicate with each other. The goal of a team is to knock down all of the opponents. Towards this goal, the agents place bombs to destroy wooden walls and collect power-up items that might appear from those wooden walls, while avoiding flames and attacking opponents. See Figure 1 (b) for an example of the board in the middle of the game.

In this work, we investigate the importance of ethnicity in colorectal cancer survivability prediction using machine learning techniques and the SEER cancer incidence database. We compare model performances for 2-year survivability prediction and feature importance rankings between Hispanic, White, and mixed patient populations. Our models consistently perform better on single-ethnicity populations and provide different feature importance rankings when trained in different populations. Additionally, we show our models achieve higher Area Under Curve (AUC) score than the best reported in the literature. We also apply imbalanced classification techniques to improve classification performance when the number of patients who have survived from colorectal cancer is much larger than who have not. These results provide evidence in favor for increased consideration of patient ethnicity in cancer survivability prediction, and for more personalized medicine in general.

Artificial intelligence is giving scientists new hope for studying the habitability of planets, in a study from astronomers Chris Lam and David Kipping. Their work looks at so-called "Tatooines," and uses machine learning techniques to calculate how likely such planets are to survive into stable orbits. The study is published in the journal Monthly Notices of the Royal Astronomical Society. Circumbinary planets are those planets that orbit two stars instead of just one, much like the fictional planet Tatooine in the Star Wars franchise. Tens of these planets have so far been discovered, but working out whether they may be habitable or not can be difficult.

When his father was diagnosed with stage IV, non-operable gastric cancer in 2007, Dr. Dimitris Bertsimas knew that combination chemotherapy was the best course of treatment. He visited several of the leading cancer hospitals in the nation--Dana Farber, Massachusetts General, MD Anderson and Memorial Sloan Kettering--to see what specific therapies they would propose for his father. "They each told me very distinct therapies, almost with no drugs in common," says Bertsimas. "I didn't know how to compare them." So Bertsimas, who is a professor of operational research at MIT did a simple back-of-the-envelope calculation.